© 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-16K
    7. 1004
    Prev
    Next
    INDEX
    Explanations

    conditional logic and loops

    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_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
    閲
    1.18
     قامت
    1.18
    ックレス
    1.11
    震撼
    1.11
    蒞
    1.10
     অতুল
    1.09
     جانب
    1.09
     真
    1.09
    ކ
    1.09
    非常的
    1.08
    POSITIVE LOGITS
    elif
    1.19
     else
    1.17
    Otherwise
    1.12
    else
    1.12
     Otherwise
    1.07
     otherwise
    1.01
     elif
    0.99
     ELSE
    0.97
     others
    0.95
    otherwise
    0.93
    Activations Density 0.003%

    No Known Activations