© 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. 143982
    Prev
    Next
    INDEX
    Explanations

    obviously decide

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

    understanding why

    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
     округа
    0.50
    之类的
    0.49
    OA
    0.46
     বলুন
    0.45
    ¹.
    0.44
     stat
    0.43
    ivers
    0.43
    !
    0.43
    នៅ
    0.42
     ойношот
    0.42
    POSITIVE LOGITS
     രീതി
    0.56
     pozycji
    0.49
     Vicky
    0.48
     décide
    0.47
    ختار
    0.45
     méthodes
    0.45
    რივი
    0.45
     Galerie
    0.45
    стин
    0.45
     방법에
    0.45
    Activations Density 0.001%

    No Known Activations