© 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. 197747
    Prev
    Next
    INDEX
    Explanations

    favorable position

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

    checking off boxes

    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
     retra
    0.52
    ූර්
    0.49
     salas
    0.48
     VT
    0.47
     koch
    0.46
     limites
    0.46
     vt
    0.46
    ;
    0.46
     placas
    0.46
     filtr
    0.45
    POSITIVE LOGITS
     Chronicle
    0.45
     ক্রস
    0.44
     Lawyers
    0.44
    enemies
    0.44
    hattim
    0.44
    defeated
    0.44
     Glossary
    0.44
     জীবনী
    0.43
    বী
    0.43
    aspx
    0.43
    Activations Density 0.000%

    No Known Activations