© 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. 74392
    Prev
    Next
    INDEX
    Explanations

    Sas, SAS, Sass variations

    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
    鼕
    -3.53
    髎
    -3.17
    钐
    -3.00
     But
    -2.95
    尛
    -2.92
     墊
    -2.84
     superfí
    -2.81
    廔
    -2.81
    附近的
    -2.78
     Clientes
    -2.77
    POSITIVE LOGITS
    and
    3.11
    In
    3.11
    5
    3.09
    8
    3.05
    6
    2.97
    O
    2.75
    is
    2.73
    -
    2.70
    L
    2.69
    C
    2.67
    Activations Density 0.005%

    No Known Activations