© 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. 8889
    Prev
    Next
    INDEX
    Explanations

    directions and acronyms

    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
    9
    -1.91
    (
    -1.82
    In
    -1.72
    p
    -1.71
    ”，
    -1.65
    pography
    -1.65
    8
    -1.63
    t
    -1.51
    Продам
    -1.50
    新的
    -1.49
    POSITIVE LOGITS
     to
    1.88
    dlo
    1.72
     niewiel
    1.71
     mały
    1.67
    dci
    1.66
    damen
    1.60
    wwe
    1.59
    蛲
    1.56
    colori
    1.55
    mali
    1.55
    Activations Density 0.198%

    No Known Activations