© 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. 66729
    Prev
    Next
    INDEX
    Explanations

    disclosure relates to

    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
    '
    -3.14
    x
    -2.56
    一旁
    -2.52
    y
    -2.47
    v
    -2.42
    ar
    -2.41
    子供が
    -2.31
    ir
    -2.30
    is
    -2.30
    -
    -2.23
    POSITIVE LOGITS
    ”:
    2.77
    噚
    2.72
    攆
    2.56
    驁
    2.55
    ).
    2.55
    ”،
    2.53
    摃
    2.45
    ሷ
    2.45
    蚴
    2.45
    ”),
    2.34
    Activations Density 0.008%

    No Known Activations