© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 759
    Prev
    Next
    INDEX
    Explanations

    python imports and raw strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <end_of_turn>
    1.06
    APPROVED
    1.03
    bokeh
    1.01
     inco
    0.98
     anuv
    0.96
    Qw
    0.95
     ironically
    0.90
     unreasonably
    0.89
     shockingly
    0.89
     почти
    0.89
    POSITIVE LOGITS
     denotes
    0.83
    ?
    0.80
     যেসব
    0.79
    các
    0.79
    های
    0.78
     các
    0.78
     suatu
    0.76
     geest
    0.76
     terjadinya
    0.76
     Các
    0.74
    Activations Density 1.546%

    No Known Activations