© 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. 75670
    Prev
    Next
    INDEX
    Explanations

    problem or

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

    fundamentally different actions

    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
    r
    0.51
    behavior
    0.48
    verständ
    0.47
    support
    0.46
    amiliar
    0.45
    propri
    0.45
    ässig
    0.45
    stdout
    0.45
     Anyways
    0.44
    assemble
    0.44
    POSITIVE LOGITS
    逺
    0.52
     respectivas
    0.49
     pter
    0.48
    サー
    0.47
     grafo
    0.46
     встречи
    0.45
     arrivals
    0.44
    ضی
    0.43
    クリスマス
    0.43
     jarak
    0.43
    Activations Density 0.000%

    No Known Activations