© 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. 10-GEMMASCOPE-RES-131K
    7. 11945
    Prev
    Next
    INDEX
    Explanations

    Someone's action

    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_10/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
     visualización
    -1.79
     verificación
    -1.77
    beratung
    -1.70
     visibilidad
    -1.60
     navegación
    -1.59
     detección
    -1.59
     difusión
    -1.58
    ledes
    -1.57
    ſſel
    -1.56
     demás
    -1.55
    POSITIVE LOGITS
     as
    2.05
    although
    1.72
     руках
    1.67
     Someone
    1.55
    ’,
    1.53
     What
    1.52
    🕗
    1.52
    中でも
    1.51
    鋮
    1.49
    周泽
    1.46
    Activations Density 0.020%

    No Known Activations