© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177335
    Prev
    Next
    INDEX
    Explanations

    shut it off

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

    advertising and ads

    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
     prefque
    0.59
    ብሰ
    0.53
    LLI
    0.51
    дей
    0.50
     sentença
    0.49
    CUSSION
    0.48
    ๚
    0.48
    OCCO
    0.48
    binghamton
    0.48
    лянчук
    0.47
    POSITIVE LOGITS
     and
    0.51
     Earth
    0.51
     և
    0.50
     Islamic
    0.49
     Housing
    0.49
     Media
    0.48
     Mỗi
    0.47
     of
    0.46
     của
    0.46
     UK
    0.46
    Activations Density 0.000%

    No Known Activations