© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    content of that nature

    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_17_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
    :**
    0.79
    :*
    0.72
    **:
    0.62
    ：
    0.62
    ：「
    0.61
    :
    0.61
    :)
    0.58
    None
    0.58
     :
    0.57
    *:
    0.57
    POSITIVE LOGITS
    あらゆる
    0.79
     خز
    0.79
     labyrinth
    0.78
     moindre
    0.77
     calmer
    0.76
     impenetrable
    0.75
    вары
    0.74
    toLowerCase
    0.74
     bloodstream
    0.73
    各大
    0.72
    Activations Density 0.145%

    No Known Activations