© 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. 56849
    Prev
    Next
    INDEX
    Explanations

    upcoming commercial

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

    non-english characters or code structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Buildings
    0.46
    <i>
    0.42
    Genus
    0.41
    とも
    0.41
    なる
    0.40
    flop
    0.40
    َالَ
    0.40
    flatten
    0.39
    кам
    0.39
     Eltern
    0.39
    POSITIVE LOGITS
     해서
    0.57
    ania
    0.54
    z
    0.54
     레
    0.52
     노트
    0.51
     도전
    0.50
    ISSU
    0.49
    inia
    0.48
     necessitates
    0.47
     페
    0.47
    Activations Density 0.001%

    No Known Activations