© 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. 95970
    Prev
    Next
    INDEX
    Explanations

    pairs or sequences

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

    domain administration, majestic creatures, code imports

    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
     weiterhin
    0.49
     franchising
    0.45
    },\
    0.44
     tenements
    0.44
     fastening
    0.44
     страхо
    0.44
     بالإضافة
    0.43
    ，
    0.43
    Build
    0.43
    cycled
    0.43
    POSITIVE LOGITS
    شل
    0.52
    کو
    0.52
    کر
    0.50
     stalemate
    0.48
    یان
    0.46
    ürgen
    0.45
     scena
    0.45
     druż
    0.45
    ייה
    0.45
    اداسی
    0.44
    Activations Density 0.001%

    No Known Activations