© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 204
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline and numbers

    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
    -)
    0.85
    ього
    0.78
     molar
    0.75
     spoiling
    0.75
     overpower
    0.74
     Wipe
    0.74
     Founder
    0.73
    -]
    0.73
     physically
    0.73
    -,
    0.73
    POSITIVE LOGITS
    beans
    0.86
    .*;
    0.72
     import
    0.71
    alliance
    0.71
    foundation
    0.69
    inston
    0.66
    bom
    0.64
    fox
    0.62
     documentación
    0.61
    的消息
    0.61
    Activations Density 0.115%

    No Known Activations