© 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. 44290
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

    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
    分からない
    -2.23
    떳
    -2.20
     Fähigkeit
    -2.08
     используют
    -2.05
    わからない
    -2.03
     razões
    -2.03
    戗
    -2.02
     Näch
    -1.99
     a
    -1.98
     Bagaimana
    -1.98
    POSITIVE LOGITS
    ⁃
    2.17
     nive
    1.96
    hibits
    1.95
    hibitor
    1.91
     parís
    1.87
    ・「
    1.84
    PUESTA
    1.82
     and
    1.81
    formatics
    1.81
    🗓
    1.80
    Activations Density 0.018%

    No Known Activations