© 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. 7549
    Prev
    Next
    INDEX
    Explanations

    pronouns and god

    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
     dwóch
    -1.45
    warnai
    -1.24
     FBref
    -1.22
    corbic
    -1.19
     trzech
    -1.19
    alım
    -1.13
     naszej
    -1.13
     sonhos
    -1.12
     koncentr
    -1.12
     obuv
    -1.11
    POSITIVE LOGITS
    </h2>
    1.22
     in
    1.20
    搖
    1.15
    顛
    1.09
    appliquer
    1.09
    ラメ
    1.05
     princi
    1.03
    lcccccc
    0.99
     are
    0.98
     epoca
    0.98
    Activations Density 0.075%

    No Known Activations