© 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. 207210
    Prev
    Next
    INDEX
    Explanations

    ways to find

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

    widely understood, name, location, whispered quotes

    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
    на
    0.60
     Реа
    0.57
    า
    0.50
    ня
    0.47
    追
    0.46
     počet
    0.46
     emo
    0.46
     реали
    0.45
     メール
    0.45
    ين
    0.45
    POSITIVE LOGITS
    ducting
    0.52
    ,’
    0.51
     تھ
    0.49
    cted
    0.47
    ’;
    0.47
    ortex
    0.44
     penetration
    0.43
    gini
    0.43
     signified
    0.43
    orescence
    0.43
    Activations Density 0.000%

    No Known Activations