© 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. 235334
    Prev
    Next
    INDEX
    Explanations

    secure or available

    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
     بنا
    0.46
    ோவின்
    0.45
    ھ
    0.45
     belliger
    0.44
     synthes
    0.44
     travailleurs
    0.44
    敵
    0.44
    ᓂ
    0.44
     graffiti
    0.43
    EndTime
    0.43
    POSITIVE LOGITS
    rasında
    0.54
    ozat
    0.52
    rae
    0.48
    B
    0.48
    umuz
    0.47
    CAD
    0.46
    A
    0.46
     Formulas
    0.46
    Jf
    0.46
    brook
    0.46
    Activations Density 0.000%

    No Known Activations