© 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. 52125
    Prev
    Next
    INDEX
    Explanations

    games and championships

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

    diagnose, update, monitor, troubleshoot, provision, activate

    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
    July
    0.52
     Julie
    0.51
     hyaluronic
    0.50
     jul
    0.47
     grandi
    0.46
     guidelines
    0.46
     downsides
    0.46
    a
    0.46
     hypocrisy
    0.45
    Julie
    0.45
    POSITIVE LOGITS
    ㄢ
    0.54
    ərə
    0.48
    xffff
    0.47
    надцать
    0.47
    ાઇલ
    0.46
    ênd
    0.46
     садо
    0.46
    逻
    0.45
    єн
    0.45
    ạm
    0.45
    Activations Density 0.000%

    No Known Activations