© 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. 92181
    Prev
    Next
    INDEX
    Explanations

    km, free, subject

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

    hindering or contact

    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
     armado
    0.53
    на
    0.51
     オリ
    0.49
    }_{+}\
    0.48
     रिप्रोडक्शन
    0.47
    াকাছি
    0.47
    scrollbar
    0.47
     アルミ
    0.47
    त्रियों
    0.46
     அந்த
    0.45
    POSITIVE LOGITS
    í
    0.59
    ö
    0.57
     poet
    0.56
    ASP
    0.52
    ā
    0.51
    ing
    0.50
    al
    0.49
     in
    0.48
    ii
    0.48
     Agg
    0.46
    Activations Density 0.000%

    No Known Activations