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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1458
    Prev
    Next
    INDEX
    Explanations

    following instructions carefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dodgers
    1.61
     Agile
    1.55
     KPI
    1.54
     bloss
    1.54
    ◟
    1.53
     bilder
    1.52
     kvalit
    1.52
    ImageAsset
    1.50
     ""<
    1.50
     ELISA
    1.50
    POSITIVE LOGITS
    enaries
    1.60
    ں
    1.43
    isti
    1.39
    icycle
    1.33
    umba
    1.30
    azin
    1.29
    istan
    1.29
    izate
    1.29
    ीय
    1.29
    ოში
    1.27
    Activations Density 0.001%

    No Known Activations