© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149473
    Prev
    Next
    INDEX
    Explanations

    sufficient

    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_29_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
     Leaf
    0.65
    
    0.62
    Baked
    0.62
    Blocked
    0.62
    0.61
    ("%
    0.60
    Meeting
    0.60
    enery
    0.60
    
    0.59
    Bien
    0.59
    POSITIVE LOGITS
     vouchers
    0.71
     crystals
    0.69
    ajú
    0.68
     vowels
    0.68
     پیچھے
    0.66
     yǔ
    0.66
     Crystals
    0.65
     windshield
    0.65
     conscious
    0.64
     waxes
    0.64
    Activations Density 0.003%

    No Known Activations