© 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. 100907
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
    ➚
    -1.59
    썽
    -1.48
    耵
    -1.45
    ่วย
    -1.38
     Its
    -1.35
    ¡¡
    -1.35
    だったり
    -1.30
    toi
    -1.30
     which
    -1.30
     it
    -1.27
    POSITIVE LOGITS
    This
    1.77
    These
    1.74
    龗
    1.57
    Most
    1.55
    Моя
    1.54
    Правила
    1.53
    Two
    1.52
     tästä
    1.50
    Жизнь
    1.50
    来年
    1.48
    Activations Density 0.031%

    No Known Activations