© 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. 167843
    Prev
    Next
    INDEX
    Explanations

    spelling variations

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

    control version

    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
     échelle
    0.54
     ā
    0.51
     skala
    0.50
     SCALE
    0.48
     скорости
    0.47
     uș
    0.47
     İ
    0.47
     О
    0.46
     İslam
    0.46
     scale
    0.46
    POSITIVE LOGITS
    compensation
    0.48
    adapt
    0.47
    གས་
    0.47
    piano
    0.45
    radians
    0.45
    respect
    0.44
    cipl
    0.43
    eby
    0.43
    relaxed
    0.43
    coef
    0.42
    Activations Density 0.000%

    No Known Activations