© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3420
    Prev
    Next
    INDEX
    Explanations

    role in

    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
    ’
    0.96
    '
    0.72
    \
    0.70
    I
    0.61
    y
    0.59
    line
    0.57
    我们
    0.56
    da
    0.56
    liers
    0.56
    perfect
    0.55
    POSITIVE LOGITS
    of
    0.71
     nettoy
    0.63
    وع
    0.62
     seus
    0.59
     dépassant
    0.59
     restaur
    0.59
    闶
    0.58
     pendek
    0.58
    тите
    0.57
    ایش
    0.57
    Activations Density 0.002%

    No Known Activations