© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46614
    Prev
    Next
    INDEX
    Explanations

    japanese honorifics san, chan, sama

    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_16_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
     primeiros
    0.73
     vésicules
    0.70
     других
    0.68
    ۳
    0.68
     individus
    0.67
    𝒂
    0.66
    の原因
    0.65
    бка
    0.65
    odha
    0.65
    ėmis
    0.64
    POSITIVE LOGITS
    es
    0.72
     in
    0.70
    scapes
    0.59
    s
    0.59
     enorm
    0.57
    देश
    0.55
    Bar
    0.54
    Ref
    0.54
     defiance
    0.53
    Dist
    0.53
    Activations Density 0.001%

    No Known Activations