© 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. 45137
    Prev
    Next
    INDEX
    Explanations

    foreign start words

    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
    p
    -2.86
    *
    -2.81
    b
    -2.81
    or
    -2.80
    “
    -2.73
    。
    -2.70
    何度も
    -2.50
    ଽ
    -2.45
    (
    -2.42
    \
    -2.42
    POSITIVE LOGITS
    䊐
    2.53
    镒
    2.48
    푢
    2.45
    ႏ
    2.44
    значно
    2.42
    忄
    2.42
     They
    2.41
    )
    2.39
    zember
    2.36
    месте
    2.36
    Activations Density 0.000%

    No Known Activations