© 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. 212602
    Prev
    Next
    INDEX
    Explanations

    and safely and securely

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

    address different

    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
     완료
    0.57
     좌
    0.51
     회
    0.48
    avras
    0.47
     마무리
    0.47
    窣
    0.47
     образова
    0.46
     지속
    0.46
    ,_-
    0.46
     සිය
    0.45
    POSITIVE LOGITS
    طيع
    0.52
     cx
    0.49
     aque
    0.46
     tato
    0.46
     sabores
    0.45
    ف
    0.45
     glandes
    0.44
    يح
    0.44
     redund
    0.43
     ston
    0.43
    Activations Density 0.001%

    No Known Activations