© 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. 85327
    Prev
    Next
    INDEX
    Explanations

    Angolan military; infrastructure; approval

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

    scheduling and management

    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
    ᑉ
    0.48
     queen
    0.47
     लैब
    0.44
     therm
    0.44
    皇后
    0.43
    传染
    0.42
    မ့်
    0.42
     MUI
    0.41
     hoher
    0.41
    नाज
    0.41
    POSITIVE LOGITS
    -”
    0.52
    ere
    0.49
    acci
    0.48
     allotments
    0.47
    ace
    0.46
    -"
    0.46
    ular
    0.45
    ಲಿ
    0.44
    Infrastructure
    0.44
    eree
    0.44
    Activations Density 0.000%

    No Known Activations