© 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. 86186
    Prev
    Next
    INDEX
    Explanations

    Belize

    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
    be
    -2.67
    ”:
    -2.66
    b
    -2.58
    )”
    -2.53
     &
    -2.20
     have
    -2.20
    )”.
    -2.14
     on
    -2.11
    ”?
    -2.11
    ):
    -2.08
    POSITIVE LOGITS
    ݯ
    2.66
    怎么说
    2.63
    และ
    2.56
    椟
    2.52
     colher
    2.48
    jewództ
    2.45
     mês
    2.44
     pôr
    2.39
    腚
    2.38
    眛
    2.38
    Activations Density 0.000%

    No Known Activations