© 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. 42694
    Prev
    Next
    INDEX
    Explanations

    names with rick or carrick

    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
    In
    -2.83
    *
    -2.56
     halben
    -2.55
    You
    -2.53
     einzigen
    -2.47
    嫵
    -2.45
    ى
    -2.44
     painstaking
    -2.33
     we
    -2.22
     technically
    -2.22
    POSITIVE LOGITS
    巨大的
    2.52
    r
    2.44
    rick
    2.44
    柃
    2.39
    ’,
    2.33
    珰
    2.30
    owi
    2.27
     ガーデン
    2.25
    rophes
    2.25
     για
    2.25
    Activations Density 0.008%

    No Known Activations