© 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. 127825
    Prev
    Next
    INDEX
    Explanations

    `charset` or `inline` or `audi`

    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
    ing
    -2.98
    他们在
    -2.80
    en
    -2.66
    P
    -2.61
    if
    -2.56
     have
    -2.44
     Of
    -2.44
    is
    -2.38
    h
    -2.36
    .,
    -2.34
    POSITIVE LOGITS
     และ
    2.80
    罍
    2.67
    蟊
    2.66
    ных
    2.55
    และ
    2.44
    spection
    2.39
    鎹
    2.34
     expériences
    2.33
    LLLL
    2.33
     boîtes
    2.31
    Activations Density 0.003%

    No Known Activations