© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71740
    Prev
    Next
    INDEX
    Explanations

    Beyond + word

    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
    齜
    -2.30
     poderosa
    -2.20
    狲
    -1.99
    鴬
    -1.98
     dividida
    -1.98
    臜
    -1.95
     belang
    -1.95
    ließen
    -1.95
    盌
    -1.95
     cheia
    -1.91
    POSITIVE LOGITS
    s
    3.11
    n
    2.64
    It
    2.52
    你
    2.45
    There
    2.36
    That
    2.28
    Beyond
    2.25
    After
    2.23
    The
    2.20
    m
    2.20
    Activations Density 0.010%

    No Known Activations