© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56261
    Prev
    Next
    INDEX
    Explanations

    analyzes asks opinion evaluates

    np_acts-logits-general · gemini-2.5-flash-lite

    . or )*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     wretched
    0.34
     ד
    0.33
    ेल
    0.32
    lesen
    0.31
    }&=
    0.31
    בת
    0.31
    팡
    0.31
    ォ
    0.30
    bauen
    0.30
     ಮನೆ
    0.30
    POSITIVE LOGITS
     describes
    0.28
     examines
    0.26
    顶
    0.26
     in
    0.26
    检验
    0.26
     employs
    0.24
     evaluates
    0.24
     underlies
    0.24
     myosin
    0.24
     validates
    0.24
    Activations Density 0.167%

    No Known Activations