© 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. 7702
    Prev
    Next
    INDEX
    Explanations

    end of clauses

    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
     one
    -1.63
    saya
    -1.34
    誑
    -1.29
    chọn
    -1.28
     EVERY
    -1.26
    besos
    -1.26
    jangan
    -1.24
     some
    -1.21
     bleue
    -1.20
     丘
    -1.20
    POSITIVE LOGITS
     but
    2.05
     renowned
    1.82
     famed
    1.64
     revered
    1.57
     vostri
    1.56
    ℣
    1.56
     quando
    1.54
     nawet
    1.39
     distinctive
    1.38
     about
    1.38
    Activations Density 0.015%

    No Known Activations