© 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. 22-GEMMASCOPE-RES-131K
    7. 65599
    Prev
    Next
    INDEX
    Explanations

    AI module, menu, place name, chapter

    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_22/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
    several
    -1.88
    seems
    -1.84
    extremely
    -1.83
    trying
    -1.79
    えっ
    -1.78
    discussed
    -1.70
    𐄁
    -1.65
    putting
    -1.64
    commonly
    -1.64
    apparently
    -1.60
    POSITIVE LOGITS
     on
    2.25
     with
    1.99
     without
    1.87
     at
    1.75
     after
    1.70
     provides
    1.66
     provide
    1.64
     gives
    1.63
     epitom
    1.61
     taking
    1.59
    Activations Density 0.013%

    No Known Activations