© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138898
    Prev
    Next
    INDEX
    Explanations

    remote connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    Z
    0.46
    dine
    0.42
     poems
    0.42
    MER
    0.42
     предпоч
    0.42
    Poems
    0.42
    ELLE
    0.41
    ia
    0.41
    MON
    0.41
    G
    0.41
    POSITIVE LOGITS
     développ
    0.47
    lardır
    0.47
     trasform
    0.44
    ټر
    0.43
    iotsitewise
    0.42
     brinqu
    0.42
     appel
    0.41
     renou
    0.41
     breaches
    0.41
    کرات
    0.41
    Activations Density 0.007%

    No Known Activations