© 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. 529
    Prev
    Next
    INDEX
    Explanations

    lists and categories

    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
     aortic
    0.75
    наче
    0.74
     unsteady
    0.70
     publicKey
    0.69
     mixture
    0.69
     digestive
    0.67
    <0xAD>
    0.66
     vertex
    0.65
     custody
    0.65
     obesity
    0.65
    POSITIVE LOGITS
    )।
    0.67
    ellingen
    0.62
    存于互联网档案馆
    0.62
     گزار
    0.62
     zac
    0.60
    bungen
    0.58
     Etat
    0.57
    orange
    0.57
    㪯
    0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.56
    Activations Density 0.047%

    No Known Activations