© 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. 119758
    Prev
    Next
    INDEX
    Explanations

    DR of countries

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

    manage separately

    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
     gripped
    0.46
    デオ
    0.45
    対処
    0.44
     가게
    0.44
    奏
    0.44
    CV
    0.43
     generalizing
    0.43
    ]$,
    0.42
     monotonicity
    0.42
     employeeService
    0.42
    POSITIVE LOGITS
     Suffolk
    0.52
     ay
    0.51
     Ay
    0.50
    ingen
    0.50
     as
    0.49
    রাশ
    0.48
     Opera
    0.47
     Ank
    0.46
     Over
    0.46
    optim
    0.46
    Activations Density 0.001%

    No Known Activations