© 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. 109520
    Prev
    Next
    INDEX
    Explanations

    whenwhen

    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
    FBSDKSettings
    0.52
    ),]),
    0.51
     doute
    0.48
    ्तार
    0.48
    წიფ
    0.47
     تاسو
    0.47
    اران
    0.47
     партії
    0.47
    მწიფ
    0.46
    дку
    0.45
    POSITIVE LOGITS
    ine
    0.48
    ./
    0.45
    போது
    0.43
    US
    0.43
     -
    0.42
    pet
    0.42
    ey
    0.42
     Heraus
    0.42
    <u>
    0.42
    z
    0.41
    Activations Density 0.005%

    No Known Activations