© 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. 7960
    Prev
    Next
    INDEX
    Explanations

    introduces listed items

    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
    iamo
    -1.43
    sequently
    -1.41
    ఱ
    -1.39
    れば
    -1.37
    Such
    -1.36
    isering
    -1.35
     diesem
    -1.34
     такое
    -1.33
    To
    -1.32
    については
    -1.30
    POSITIVE LOGITS
     a
    1.62
    ”:
    1.34
    isseaux
    1.22
     inglês
    1.20
     “...
    1.19
     Allocate
    1.17
     أما
    1.14
     coiffure
    1.14
     but
    1.11
     CHA
    1.11
    Activations Density 0.042%

    No Known Activations