© 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. 127968
    Prev
    Next
    INDEX
    Explanations

    following after Who

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

    from investments, Week Intensive, Every Monday

    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
    beza
    0.53
    cao
    0.51
    WebGL
    0.47
     milioane
    0.47
     mathematicians
    0.46
    isola
    0.44
     $('
    0.44
    jaan
    0.44
     lakes
    0.44
    citizen
    0.43
    POSITIVE LOGITS
     Serp
    0.49
    ̡
    0.48
     humiliation
    0.47
     Thurston
    0.46
    停
    0.46
    र्तन
    0.45
    ീ
    0.44
    шення
    0.43
     cum
    0.43
    лки
    0.43
    Activations Density 0.000%

    No Known Activations