© 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. 20916
    Prev
    Next
    INDEX
    Explanations

    pecking, pecker, Peclet

    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
    The
    -3.86
    I
    -3.02
    re
    -2.91
    They
    -2.86
    It
    -2.83
     But
    -2.72
    la
    -2.66
    ?”
    -2.64
    u
    -2.61
    en
    -2.59
    POSITIVE LOGITS
    𞤥
    2.44
    栝
    2.31
    垕
    2.25
    酲
    2.20
    Rumble
    2.20
    趼
    2.19
    飏
    2.17
    轫
    2.14
    牁
    2.14
     gelb
    2.09
    Activations Density 0.002%

    No Known Activations