© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133137
    Prev
    Next
    INDEX
    Explanations

    wood table or talk around

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

    business statistics programming argumentation

    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
    trk
    0.54
    𝑡
    0.49
    ᴦ
    0.49
    сторінку
    0.48
    bbc
    0.47
    ᴄ
    0.47
    𝒕
    0.47
     Фила
    0.46
    𝟯
    0.46
    трибу
    0.46
    POSITIVE LOGITS
     nook
    0.48
    す
    0.48
    Getting
    0.46
     waves
    0.44
    聘
    0.44
    Finding
    0.44
     mysteries
    0.44
     obiettivo
    0.44
     Wave
    0.43
    These
    0.43
    Activations Density 0.001%

    No Known Activations