© 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. 91144
    Prev
    Next
    INDEX
    Explanations

    language and writing

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

    lists of descriptive phrases

    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
     phía
    0.51
    ói
    0.49
     গিয়ে
    0.46
    security
    0.46
     后
    0.45
    íticos
    0.45
    duit
    0.45
    بيت
    0.45
    要在
    0.44
    తి
    0.44
    POSITIVE LOGITS
    普通の
    0.52
     লিখিয়াছেন
    0.44
    اک
    0.44
    少なくとも
    0.44
    ㄹ
    0.44
     schreiben
    0.43
     surn
    0.43
    जनिक
    0.43
    詳しい
    0.43
     writable
    0.42
    Activations Density 0.000%

    No Known Activations