© 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. 2590
    Prev
    Next
    INDEX
    Explanations

    You are

    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
    ሱስ
    0.95
    asida
    0.89
    ര്‍
    0.86
     appellants
    0.82
    imų
    0.81
    人们
    0.80
    Instances
    0.79
    除
    0.79
    addir
    0.78
    myItemType
    0.78
    POSITIVE LOGITS
     own
    1.24
     thoughts
    1.15
     wanted
    0.94
     corrected
    0.91
     humbly
    0.90
     spent
    0.89
     thinks
    0.88
     couldn
    0.87
     heard
    0.87
     didn
    0.86
    Activations Density 0.281%

    No Known Activations