© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102775
    Prev
    Next
    INDEX
    Explanations

    boolean or zero values

    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_34/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
     potrebbero
    -1.11
    μό
    -1.05
     dovrebbero
    -1.01
    providedIn
    -0.93
    *}\
    -0.92
     podoba
    -0.88
     komfort
    -0.84
     personnalisés
    -0.84
    These
    -0.84
    </tfoot>
    -0.84
    POSITIVE LOGITS
    btnLogin
    0.95
    сшта
    0.94
    pherds
    0.93
     ("%
    0.93
     LABORATOR
    0.92
    shame
    0.90
    Lecturer
    0.90
    Sog
    0.90
     geval
    0.88
     TÉ
    0.87
    Activations Density 0.011%

    No Known Activations