© 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-262K
    7. 19360
    Prev
    Next
    INDEX
    Explanations

    when holding

    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_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
    aujourd
    0.96
     financeiros
    0.95
    లను
    0.95
    枓
    0.92
     военных
    0.92
     රා
    0.92
     Certains
    0.92
     destes
    0.92
     pagare
    0.91
     oorlog
    0.91
    POSITIVE LOGITS
    z
    0.81
    zyme
    0.80
    ix
    0.77
    zs
    0.76
    b
    0.75
     b
    0.72
     inside
    0.70
     short
    0.70
     previously
    0.70
     swimming
    0.69
    Activations Density 0.001%

    No Known Activations