© 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. 792
    Prev
    Next
    INDEX
    Explanations

    code separators or lists

    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
     injury
    0.71
     interconnected
    0.70
     polysaccharides
    0.69
     á
    0.67
     Alpine
    0.67
     tuning
    0.66
     Linux
    0.65
     terrestrial
    0.65
     terpen
    0.65
     culminating
    0.65
    POSITIVE LOGITS
    Pedido
    0.88
    ]=
    0.80
    )}"
    0.78
    Info
    0.77
    )">
    0.77
    Or
    0.76
     മുത
    0.76
    $}
    0.74
     бать
    0.73
    找不到
    0.72
    Activations Density 0.075%

    No Known Activations