© 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. 13400
    Prev
    Next
    INDEX
    Explanations

    SQL variables starting with @

    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
    ى
    0.74
    uted
    0.69
    is
    0.61
    ब्रे
    0.61
    к
    0.60
    ят
    0.59
    ץ
    0.56
    ay
    0.55
    imbo
    0.55
    ے
    0.55
    POSITIVE LOGITS
    t
    0.92
    s
    0.82
    d
    0.75
    </h4>
    0.74
    nd
    0.70
    <0x0D>
    0.70
     Lakers
    0.70
     in
    0.68
    tà
    0.68
     from
    0.67
    Activations Density 0.002%

    No Known Activations