© 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. 45056
    Prev
    Next
    INDEX
    Explanations

    generic type declarations

    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
     have
    -1.47
     more
    -1.45
    ↵
    -1.36
     most
    -1.35
     there
    -1.31
     some
    -1.30
     use
    -1.30
    拢
    -1.29
     many
    -1.28
     coreana
    -1.26
    POSITIVE LOGITS
    だけでなく
    1.83
    7
    1.52
     jego
    1.49
    6
    1.48
     embaj
    1.48
     uniquement
    1.47
     incluyendo
    1.46
     její
    1.46
     berücksich
    1.43
     Empfang
    1.43
    Activations Density 0.010%

    No Known Activations