© 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. 72686
    Prev
    Next
    INDEX
    Explanations

    data structures and code snippets

    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
    gerne
    -1.02
    requested
    -0.95
    czyki
    -0.91
    rédients
    -0.85
    rk
    -0.85
     SEVEN
    -0.82
    Παρα
    -0.82
    ırlar
    -0.81
    achite
    -0.81
    edback
    -0.81
    POSITIVE LOGITS
     our
    0.86
     makeshift
    0.85
     áreas
    0.83
     ]:
    0.82
     know
    0.79
     only
    0.79
     configuration
    0.77
     setup
    0.77
     circulating
    0.75
     為
    0.74
    Activations Density 0.061%

    No Known Activations