© 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. 74470
    Prev
    Next
    INDEX
    Explanations

    at all times

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

    not a or not the

    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
     もう
    0.56
    ﺝ
    0.54
    ജെ
    0.52
     つ
    0.50
    ʧ
    0.49
     infancy
    0.47
     aye
    0.47
     ಸ
    0.47
     男の子
    0.47
     Sons
    0.46
    POSITIVE LOGITS
    u
    0.52
    ULA
    0.47
    锐
    0.47
    ing
    0.45
    عب
    0.45
    不满
    0.45
    (\
    0.44
    ucho
    0.44
    如下
    0.44
    امل
    0.43
    Activations Density 0.003%

    No Known Activations