© 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. 65335
    Prev
    Next
    INDEX
    Explanations

    finance, crypto, code, names

    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
     so
    -1.37
    𝗺
    -1.36
    kız
    -1.36
     dodatk
    -1.35
    település
    -1.31
    antwo
    -1.30
     my
    -1.28
    maks
    -1.23
    rildi
    -1.23
    ？！”
    -1.23
    POSITIVE LOGITS
    детская
    1.59
    детский
    1.48
    🧫
    1.47
    parently
    1.45
    𓂂
    1.41
     bordeaux
    1.37
    盉
    1.36
     Véri
    1.35
     tendría
    1.34
     foit
    1.33
    Activations Density 0.003%

    No Known Activations