© 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. 40918
    Prev
    Next
    INDEX
    Explanations

    details about

    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
    0.40
    .
    0.39
    。
    0.39
    Ｒ
    0.34
    ark
    0.33
    U
    0.32
    ，
    0.32
    UI
    0.32
    博
    0.31
    V
    0.31
    POSITIVE LOGITS
    こうした
    0.37
    かもしれませんが
    0.35
     aiuta
    0.33
     investigador
    0.33
     menjaga
    0.32
    しましたが
    0.32
    इसलिए
    0.32
    让自己
    0.32
     стрем
    0.32
     aiutare
    0.31
    Activations Density 0.052%

    No Known Activations