© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128241
    Prev
    Next
    INDEX
    Explanations

    how should

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

    formatting symbols and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BinaryOperation
    0.50
    setInt
    0.49
     inconven
    0.43
     buttons
    0.43
    加载
    0.43
     ভট্ট
    0.42
     pact
    0.41
    ằ
    0.41
    aksanakan
    0.41
     theyre
    0.41
    POSITIVE LOGITS
     Iberian
    0.53
     Jubilee
    0.48
    翮
    0.48
     Mediterranean
    0.48
    Mediterranean
    0.48
     Noz
    0.47
     Norwich
    0.47
     PHIL
    0.46
     Panoramic
    0.46
     Westchester
    0.46
    Activations Density 0.001%

    No Known Activations