© 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. 21037
    Prev
    Next
    INDEX
    Explanations

    record deal

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

    The neuron fires on capitalized proper nouns, especially geographic locations and group names.

    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
     not
    -2.44
     about
    -2.22
     now
    -2.14
     September
    -2.06
     December
    -1.97
     October
    -1.94
     still
    -1.93
     mostly
    -1.93
     actually
    -1.91
     July
    -1.89
    POSITIVE LOGITS
     verir
    1.97
     robuste
    1.88
    }$.
    1.86
    
    1.77
    wijl
    1.73
    
    1.68
     tekno
    1.66
     debat
    1.65
    !}
    1.65
    mengen
    1.63
    Activations Density 0.155%

    No Known Activations