© 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. 108665
    Prev
    Next
    INDEX
    Explanations

    CDMA Mobile

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

    subathon

    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
    언
    0.49
     Nähe
    0.43
    られ
    0.41
     Lorsque
    0.40
    inherited
    0.40
     Fly
    0.40
    fly
    0.40
     Bildung
    0.40
    報
    0.39
     Builds
    0.39
    POSITIVE LOGITS
     upscale
    0.50
    ódigo
    0.49
    高端
    0.49
    monia
    0.48
    蛋糕
    0.47
     devono
    0.46
     furnish
    0.46
     uphol
    0.46
     NER
    0.46
    itabbam
    0.46
    Activations Density 0.001%

    No Known Activations