© 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. 70928
    Prev
    Next
    INDEX
    Explanations

    document details

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

    foreign languages and technical terms

    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
     locks
    0.40
    Bone
    0.39
     espèces
    0.39
     생
    0.38
     pher
    0.38
    πους
    0.37
    <>();
    0.36
     toàn
    0.36
     చే
    0.36
    ាក
    0.36
    POSITIVE LOGITS
     いたし
    0.50
     Honestly
    0.49
    站在
    0.48
    matis
    0.47
    subnet
    0.46
    ла
    0.46
    cambrian
    0.46
    ższ
    0.45
    케이
    0.45
    𝓪
    0.45
    Activations Density 0.000%

    No Known Activations