© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10479
    Prev
    Next
    INDEX
    Explanations

    domestic violence support

    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_22_width_16k_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
    knię
    0.96
     कहान
    0.95
    iapan
    0.93
    ⠄
    0.89
    etään
    0.88
    kon
    0.87
    kolah
    0.87
    irk
    0.86
     pequeño
    0.86
     टोल
    0.86
    POSITIVE LOGITS
    umbus
    1.23
     vertebr
    1.19
    ISTS
    1.01
    休
    1.00
    UMNS
    0.99
    nrow
    0.98
    nade
    0.97
    HEAD
    0.97
    AES
    0.97
    num
    0.97
    Activations Density 0.055%

    No Known Activations