© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    что это

    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
     cabling
    2.23
    🈂
    2.03
     tiap
    1.96
    🈯
    1.95
     leveraging
    1.94
    🚱
    1.94
     Fmat
    1.93
    ⛎
    1.91
    🕤
    1.91
    🕣
    1.89
    POSITIVE LOGITS
     по
    2.89
     с
    2.84
     не
    2.79
     о
    2.75
     на
    2.73
     в
    2.59
     при
    2.55
     из
    2.54
     ка
    2.52
     у
    2.49
    Activations Density 0.373%

    No Known Activations