© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9018
    Prev
    Next
    INDEX
    Explanations

    repetition and emphasis

    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_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
    R
    0.41
    4
    0.41
    MING
    0.40
    ाइंड
    0.39
     battled
    0.38
     виру
    0.38
     одну
    0.38
    IKV
    0.38
     Déf
    0.37
    /
    0.37
    POSITIVE LOGITS
    ....
    0.51
     nagyon
    0.50
     veldig
    0.49
     রকমের
    0.49
    .....
    0.47
     因為
    0.47
     .....
    0.45
    ............
    0.45
     helemaal
    0.45
    ങ്ങനെ
    0.45
    Activations Density 0.038%

    No Known Activations