© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    numbered list steps

    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
    ال
    0.69
     Multiple
    0.68
    ↵↵↵↵↵
    0.66
    ↵↵↵
    0.65
     Seven
    0.65
    неш
    0.64
    য়াল
    0.63
     Abandon
    0.62
     Elabor
    0.62
    ↵↵↵↵
    0.62
    POSITIVE LOGITS
     iterate
    0.98
     iteratively
    0.97
     iterating
    0.94
     Iterate
    0.88
     사용
    0.85
     iterative
    0.81
     전에
    0.80
    (
    0.80
     rename
    0.80
    Iter
    0.79
    Activations Density 0.093%

    No Known Activations