© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76614
    Prev
    Next
    INDEX
    Explanations

    municipality, town, place names

    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
     Bartlett
    -0.79
     藍
    -0.77
     MSS
    -0.77
    TW
    -0.76
    aturation
    -0.75
    WriteLiteral
    -0.74
     Velas
    -0.74
    turno
    -0.73
     hashtag
    -0.73
     toast
    -0.73
    POSITIVE LOGITS
    Grad
    0.93
     Grad
    0.81
     allegory
    0.81
     alleg
    0.77
     Hope
    0.73
     Alleg
    0.72
    三郎
    0.69
     grid
    0.69
    Resultados
    0.67
    疣
    0.67
    Activations Density 0.005%

    No Known Activations