© 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. 34-GEMMASCOPE-RES-131K
    7. 57079
    Prev
    Next
    INDEX
    Explanations

    ID assignment or field designation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     both
    -0.96
     mainly
    -0.90
     endless
    -0.90
     any
    -0.87
     almost
    -0.85
     đều
    -0.84
     generally
    -0.83
     various
    -0.82
    加減
    -0.81
     mostly
    -0.81
    POSITIVE LOGITS
    card
    1.18
     kaart
    1.09
     Card
    1.08
     of
    1.00
     card
    0.99
    лав
    0.98
    ofas
    0.98
    οντας
    0.97
    Card
    0.96
    Token
    0.96
    Activations Density 0.029%

    No Known Activations