© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113626
    Prev
    Next
    INDEX
    Explanations

    software for management and analysis

    np_acts-logits-general · gemini-2.5-flash-lite

    software product names and technical management systems, particularly in business and technology contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on capitalized software‐product names and related branded terms (e.g. “Inventory Manager™,” “service inventory management software,” or other “* Software” phrases).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     только
    -1.29
     only
    -1.27
     or
    -1.25
     primeras
    -1.23
     valoraciones
    -1.22
    Loai
    -1.18
     primera
    -1.17
     pocas
    -1.16
     vacaciones
    -1.15
     koje
    -1.13
    POSITIVE LOGITS
     madu
    1.58
     chande
    1.57
     matel
    1.52
     daer
    1.48
     strass
    1.48
     alip
    1.46
     apartament
    1.45
     timeStamp
    1.42
     kue
    1.41
     zafira
    1.41
    Activations Density 0.252%

    No Known Activations