© 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. 235488
    Prev
    Next
    INDEX
    Explanations

    jaw crusher, surfactants, Harrier

    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
     ২০২৩
    0.45
    㬶
    0.42
     modes
    0.42
    
    0.41
     隣
    0.41
     معظم
    0.40
    ['-
    0.40
    neighbors
    0.40
    ovaž
    0.39
    getto
    0.38
    POSITIVE LOGITS
    sembles
    0.45
    Import
    0.43
    '],
    0.43
    ')
    0.42
    ิง
    0.41
    EN
    0.41
    KE
    0.41
    Resolver
    0.40
    Arch
    0.40
    াক
    0.40
    Activations Density 0.001%

    No Known Activations