© 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. 85453
    Prev
    Next
    INDEX
    Explanations

    events, situations, or states

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

    encoder blocks

    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
    Men
    0.49
    ຣ
    0.48
    之为
    0.46
    Одно
    0.45
    ंदरे
    0.45
    rant
    0.44
    Density
    0.44
     основные
    0.44
    Следу
    0.43
    鐧
    0.43
    POSITIVE LOGITS
     rene
    0.44
     creates
    0.43
     Veranstaltung
    0.42
     পারিনি
    0.41
     formularios
    0.41
    OPENJDK
    0.41
     generates
    0.40
     evento
    0.40
     opgenomen
    0.40
     facilitation
    0.40
    Activations Density 0.000%

    No Known Activations