© 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. 113004
    Prev
    Next
    INDEX
    Explanations

    code and symbols

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

    whitespace characters, particularly tabs and newlines in structured technical documents.

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

    The neuron primarily activates on numeric tokens (i.e. any standalone numbers, timestamps, or measurements).

    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
    戆
    -1.98
     irmã
    -1.91
    jaqueta
    -1.82
    ༵
    -1.77
     Jenderal
    -1.76
    
    -1.76
    蒾
    -1.76
     Kerja
    -1.72
     wszyst
    -1.68
    簠
    -1.64
    POSITIVE LOGITS
     Hinblick
    1.98
     
    1.65
    傒
    1.64
    ll
    1.64
     faciliter
    1.63
     rechten
    1.60
    みます
    1.59
     Gegensatz
    1.59
     einige
    1.59
    当然
    1.59
    Activations Density 0.008%

    No Known Activations