© 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. 47917
    Prev
    Next
    INDEX
    Explanations

    in Cascadia, the confusion, full series

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

    consensual interaction and consent

    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
     waived
    0.52
     wavenumber
    0.48
    ڦ
    0.46
     UTIL
    0.46
     enters
    0.45
     genomic
    0.45
     wrongfully
    0.45
     極
    0.45
     linemen
    0.45
    ড়িয়ে
    0.44
    POSITIVE LOGITS
    یک
    0.52
    리
    0.47
    Р
    0.47
    "
    0.45
    اره
    0.45
    张
    0.45
    らせ
    0.44
    ע
    0.44
    付费
    0.44
    전
    0.44
    Activations Density 0.000%

    No Known Activations