© 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. 9987
    Prev
    Next
    INDEX
    Explanations

    give you

    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
    을
    1.42
    를
    1.19
    ী
    1.12
    కుంట
    1.11
     då
    1.07
    を下
    1.06
    を
    1.04
    ا
    1.04
    wy
    1.03
     نز
    1.02
    POSITIVE LOGITS
     περισσότε
    1.18
    عتها
    1.09
    돗
    1.02
     있도록
    1.01
    Verdict
    1.00
     Fordham
    0.99
    Il
    0.98
    可能性
    0.97
    Se
    0.97
    値を
    0.97
    Activations Density 0.002%

    No Known Activations