© 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. 2964
    Prev
    Next
    INDEX
    Explanations

    bold formatting around section titles

    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
    图
    0.32
    其余
    0.32
    Neighbors
    0.31
    Components
    0.31
    这两
    0.31
     নিউ
    0.31
     thương
    0.30
    ط
    0.30
    Infer
    0.29
    璽
    0.29
    POSITIVE LOGITS
     importantly
    0.43
     sogen
    0.40
     sogenannten
    0.36
     Ges
    0.35
     Importantly
    0.35
    been
    0.34
    yrıca
    0.34
     refrained
    0.34
    唷
    0.34
    Interestingly
    0.34
    Activations Density 0.725%

    No Known Activations