© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3726
    Prev
    Next
    INDEX
    Explanations

    stalking and stalkers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    It
    -2.61
    t
    -2.47
    .
    -2.44
    re
    -2.42
    ت
    -2.27
    In
    -2.25
    lo
    -2.25
    The
    -2.22
    [
    -2.22
    man
    -2.19
    POSITIVE LOGITS
    コミュ
    2.67
    ⬮
    2.66
    끫
    2.61
    ᠂
    2.61
    ೢ
    2.59
     podían
    2.55
    沕
    2.47
    Ꮵ
    2.47
    铩
    2.44
    ﹍﹍
    2.42
    Activations Density 0.003%

    No Known Activations