© 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. 10-GEMMASCOPE-RES-131K
    7. 66603
    Prev
    Next
    INDEX
    Explanations

    import statements and function definitions

    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_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
     and
    -1.63
    uniqlo
    -1.51
     流れ
    -1.51
    đồ
    -1.50
     harika
    -1.48
    accumulative
    -1.45
    cómo
    -1.43
    に行って
    -1.42
    nordic
    -1.41
     移動
    -1.39
    POSITIVE LOGITS
    providedIn
    1.63
    We
    1.57
    .
    1.49
    it
    1.43
    "">
    1.41
    private
    1.40
    eability
    1.37
    ron
    1.36
    >');
    1.36
    el
    1.34
    Activations Density 0.014%

    No Known Activations