© 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-65K
    7. 31579
    Prev
    Next
    INDEX
    Explanations

    method and composition descriptions

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Geometry
    0.54
    馈
    0.53
    应对
    0.51
    探测
    0.51
    辉
    0.50
    汇
    0.49
     gripper
    0.49
    堞
    0.48
    开关
    0.48
     wewnętr
    0.48
    POSITIVE LOGITS
    preferably
    0.63
     preferably
    0.59
    any
    0.54
    peptide
    0.52
    you
    0.52
    não
    0.51
    loro
    0.51
    ructose
    0.50
     Preferably
    0.50
    ementerian
    0.49
    Activations Density 0.012%

    No Known Activations