© 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. 22-GEMMASCOPE-2-RES-65K
    7. 669
    Prev
    Next
    INDEX
    Explanations

    URLs and domains

    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_22_width_65k_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
     trust
    0.77
     much
    0.69
     believe
    0.67
    o
    0.67
    टा
    0.64
    able
    0.64
    tt
    0.63
     Farms
    0.63
    t
    0.62
     carve
    0.62
    POSITIVE LOGITS
    恪
    0.85
    印刷
    0.82
    出る
    0.81
    žený
    0.81
    скім
    0.79
    <unused21>
    0.78
    <unused45>
    0.78
    
    0.77
    <unused64>
    0.77
    招
    0.77
    Activations Density 0.047%

    No Known Activations