© 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. 124793
    Prev
    Next
    INDEX
    Explanations

    editor general

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

    Later interpretations, which necessitate, people learn

    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
    ді
    0.45
    Trains
    0.44
    াইট
    0.44
    APPY
    0.44
    кме
    0.43
    지에
    0.43
    ोक
    0.42
    🎩
    0.42
     संग्रहालय
    0.42
    esan
    0.42
    POSITIVE LOGITS
     courrier
    0.47
     courage
    0.46
     solidar
    0.45
     sarcasm
    0.44
     cable
    0.43
     humor
    0.43
     also
    0.42
     deriv
    0.42
     reaction
    0.42
     discord
    0.42
    Activations Density 0.010%

    No Known Activations