© 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. 59096
    Prev
    Next
    INDEX
    Explanations

    architecture assembly board platform

    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
    怎么回事
    -1.88
    驺
    -1.74
     our
    -1.70
    螣
    -1.66
    麈
    -1.63
    珰
    -1.54
    玙
    -1.53
    汭
    -1.51
    卺
    -1.48
    虯
    -1.47
    POSITIVE LOGITS
    4
    2.23
    O
    2.16
    3
    2.08
    (
    2.05
    E
    1.93
    6
    1.85
    er
    1.81
    —
    1.81
    V
    1.73
    2
    1.72
    Activations Density 0.048%

    No Known Activations