© 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. 162902
    Prev
    Next
    INDEX
    Explanations

    Relief, eggs, driving, properly

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

    action verbs and specific nouns

    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
    as
    0.51
    c
    0.49
    s
    0.48
    os
    0.48
     யா
    0.48
    naam
    0.47
    αν
    0.46
    auh
    0.45
    ans
    0.44
    ieden
    0.44
    POSITIVE LOGITS
    堞
    0.47
     Fiesta
    0.46
    सदी
    0.44
    ポーツ
    0.43
    ಏ
    0.43
    前の
    0.43
    ুয়ারি
    0.43
     mariage
    0.43
     bao
    0.42
    convolve
    0.42
    Activations Density 0.000%

    No Known Activations