© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111548
    Prev
    Next
    INDEX
    Explanations

    navigational menus

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

    the word "menu" in technical or interface contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geſ
    -2.25
    Ꮠ
    -1.84
    ਤ
    -1.76
    peño
    -1.67
    牁
    -1.66
    boutin
    -1.63
    vamo
    -1.62
     οποίο
    -1.58
    продам
    -1.56
    髏
    -1.56
    POSITIVE LOGITS
    ଃ
    1.79
     complet
    1.69
    说得
    1.66
    辚
    1.66
    吶
    1.63
    嘮
    1.60
    ᝰ
    1.60
    🛇
    1.60
    うまく
    1.59
    鶿
    1.57
    Activations Density 0.019%

    No Known Activations