© 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. 42494
    Prev
    Next
    INDEX
    Explanations

    ITU-T, profanity, section starts

    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
    鱨
    -2.88
    𖥦
    -2.80
    鬭
    -2.69
    $,
    -2.50
     bidra
    -2.47
    es
    -2.47
    龗
    -2.45
    蚡
    -2.42
    苁
    -2.41
    tività
    -2.33
    POSITIVE LOGITS
     was
    2.67
     It
    2.50
     Its
    2.36
    ’
    2.30
    咈
    2.22
    }
    2.17
    轳
    2.11
    骉
    2.09
     be
    2.05
    “
    2.05
    Activations Density 0.000%

    No Known Activations