© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5270
    Prev
    Next
    INDEX
    Explanations

    code delimiters like `()` and `[]`

    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_31_width_16k_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
    i
    0.68
    '
    0.68
     to
    0.65
    ié
    0.65
     at
    0.60
     with
    0.58
    at
    0.57
    ெ
    0.57
    ol
    0.56
     Л
    0.56
    POSITIVE LOGITS
    .
    0.80
    ة
    0.75
     божомолу
    0.69
    ।
    0.69
    ра
    0.68
    ने
    0.67
    ле
    0.67
    ۔
    0.67
    ။
    0.66
     are
    0.66
    Activations Density 0.221%

    No Known Activations