© 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. 39238
    Prev
    Next
    INDEX
    Explanations

    lived in or with

    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
    觔
    -3.11
    鷓
    -3.11
    驀
    -3.06
    ⎆
    -3.06
    鱘
    -2.86
    梣
    -2.83
    ίζει
    -2.69
    昞
    -2.69
    迳
    -2.66
    鱻
    -2.58
    POSITIVE LOGITS
    ’
    4.44
    '
    3.75
    .
    3.20
    -
    3.16
    "
    3.11
    of
    3.06
    on
    2.92
    s
    2.80
    是
    2.72
    But
    2.58
    Activations Density 0.006%

    No Known Activations