© 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. 181338
    Prev
    Next
    INDEX
    Explanations

    organic productswinter tiresbrought officers

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

    desk, dimmer, suited, google, shrinks

    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
    et
    0.65
    '
    0.57
    t
    0.55
    ’
    0.54
    ب
    0.54
    <0x80>
    0.53
    tu
    0.52
    가
    0.51
    tk
    0.49
     assumed
    0.47
    POSITIVE LOGITS
     Anwar
    0.52
     поня
    0.48
     전에
    0.46
    ≖
    0.46
     pemilihan
    0.46
    栤
    0.46
     Charan
    0.45
    チョコ
    0.44
     maggio
    0.44
    Gosudarstvennyj
    0.44
    Activations Density 0.000%

    No Known Activations