© 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. 177016
    Prev
    Next
    INDEX
    Explanations

    including regulatory

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

    getting blocked or found

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tus
    0.47
    ess
    0.45
    tas
    0.45
    tur
    0.43
    Jeh
    0.43
    enemies
    0.42
    0.42
    )
    0.42
    el
    0.42
    TAS
    0.42
    POSITIVE LOGITS
     incidencia
    0.54
     institu
    0.52
     لیګ
    0.52
    ပို
    0.51
     Eyre
    0.51
     반지름
    0.49
     Harvey
    0.49
     Marko
    0.49
    녠
    0.49
     punctulatis
    0.49
    Activations Density 0.000%

    No Known Activations