© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35871
    Prev
    Next
    INDEX
    Explanations

    react native

    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
    Negative Logits
    O
    0.64
    to
    0.64
    3
    0.63
     (
    0.62
    И
    0.62
    ID
    0.61
    M
    0.61
    .
    0.59
    G
    0.58
    7
    0.58
    POSITIVE LOGITS
    𝒉
    0.61
    高质量
    0.59
    า
    0.57
    ]=-
    0.56
    ಳ
    0.56
     nghệ
    0.55
    o
    0.55
    ழிவு
    0.54
    )^*
    0.54
    ڑے
    0.53
    Activations Density 0.001%

    No Known Activations