© 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. 65903
    Prev
    Next
    INDEX
    Explanations

    terms and concepts

    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
    Although
    -1.27
    Since
    -1.18
     frambo
    -1.16
     Suom
    -1.16
    Québec
    -1.11
     Although
    -1.08
     ($\
    -1.08
    红的
    -1.07
    Hvor
    -1.06
    Polska
    -1.06
    POSITIVE LOGITS
     you
    1.71
    really
    1.63
     our
    1.62
     really
    1.59
     realmente
    1.48
     kinda
    1.45
     we
    1.43
     aquí
    1.42
     그리고
    1.37
    actually
    1.34
    Activations Density 0.012%

    No Known Activations