© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10450
    Prev
    Next
    INDEX
    Explanations

    AI text adventure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     summarize
    0.72
     accessToken
    0.72
     deny
    0.71
     alex
    0.70
    zuf
    0.68
     пов
    0.67
    ⊇
    0.67
     whisk
    0.67
     inflict
    0.67
     Χ
    0.67
    POSITIVE LOGITS
    atanam
    0.85
    ยายาม
    0.84
     casserole
    0.82
    SearchCV
    0.81
    Looking
    0.80
    logits
    0.80
     egen
    0.80
    Expected
    0.80
     पीने
    0.79
    Separate
    0.79
    Activations Density 0.213%

    No Known Activations