© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8369
    Prev
    Next
    INDEX
    Explanations

    change and rates

    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_9_width_262k_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
    >
    0.93
     people
    0.80
     our
    0.79
    people
    0.78
    everyone
    0.74
     dhe
    0.72
    you
    0.70
     niemand
    0.69
     everyone
    0.69
     fortsatt
    0.68
    POSITIVE LOGITS
     appreciably
    0.97
     ofthe
    0.96
     của
    0.93
    させる
    0.91
     whopping
    0.90
    Η
    0.89
     atthe
    0.89
    anée
    0.89
     obtainable
    0.88
    ΤΟ
    0.88
    Activations Density 0.354%

    No Known Activations