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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2326
    Prev
    Next
    INDEX
    Explanations

    I was

    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
     still
    -1.03
     let
    -0.88
     soon
    -0.87
    still
    -0.87
    Still
    -0.81
     pandas
    -0.81
    lty
    -0.81
     already
    -0.77
     lets
    -0.76
     Still
    -0.76
    POSITIVE LOGITS
     Communism
    0.80
    mäßigen
    0.76
    zando
    0.73
     mungkin
    0.73
    dymyr
    0.72
    ἠ
    0.71
     familiale
    0.71
    dedores
    0.71
    Evaporation
    0.70
     навіть
    0.70
    Activations Density 0.004%

    No Known Activations