© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    Vicuna

    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
    for
    0.73
    ad
    0.66
    و
    0.63
    us
    0.62
    ap
    0.61
    ف
    0.59
    and
    0.57
    im
    0.56
    as
    0.56
    er
    0.55
    POSITIVE LOGITS
     is
    0.77
    0.62
     言っ
    0.42
     taxonom
    0.42
    ゚
    0.42
     it
    0.41
     vices
    0.41
     mAbs
    0.41
     “…
    0.40
     bellows
    0.39
    Activations Density 0.272%

    No Known Activations