© 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. 35607
    Prev
    Next
    INDEX
    Explanations

    sure enough

    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
     ")
    0.73
    .}
    0.64
    .*/
    0.64
    lere
    0.62
    lene
    0.61
    )+
    0.61
    .]
    0.61
    )/
    0.61
    &&
    0.61
    ).}
    0.61
    POSITIVE LOGITS
     amort
    0.67
     was
    0.66
     Canada
    0.62
     CFC
    0.62
     ít
    0.60
    ור
    0.59
     London
    0.59
    ก
    0.59
     cohort
    0.58
    يج
    0.58
    Activations Density 0.000%

    No Known Activations