© 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. 17-GEMMASCOPE-2-RES-16K
    7. 526
    Prev
    Next
    INDEX
    Explanations

    To help

    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_17_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
    ary
    0.78
     گذ
    0.77
    igning
    0.73
    ступает
    0.72
    s
    0.71
    alone
    0.71
    are
    0.70
    itaria
    0.68
    (
    0.67
    ura
    0.66
    POSITIVE LOGITS
     ensure
    2.19
     prevent
    1.96
     avoid
    1.94
     alleviate
    1.86
     achieve
    1.84
     preclude
    1.77
     appease
    1.73
     counteract
    1.71
     facilitate
    1.71
     enhance
    1.70
    Activations Density 1.757%

    No Known Activations