© 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. 129148
    Prev
    Next
    INDEX
    Explanations

    foreign language elements

    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
    Negative Logits
     quas
    0.50
     inertial
    0.45
    รียน
    0.43
     san
    0.42
     WT
    0.42
     interstellar
    0.42
     Ā
    0.42
     Clements
    0.41
     Electric
    0.41
     Weg
    0.41
    POSITIVE LOGITS
     validType
    0.46
    те
    0.45
    μό
    0.44
    ের
    0.43
    ים
    0.42
     самого
    0.42
    є
    0.42
    мерикан
    0.41
    де
    0.41
    ங்களை
    0.41
    Activations Density 0.004%

    No Known Activations