© 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. 38380
    Prev
    Next
    INDEX
    Explanations

    model year

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

    predict outcomes

    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
    発見
    0.56
    сте
    0.53
     potenci
    0.52
    ва
    0.51
    зин
    0.50
     Моло
    0.48
    箬
    0.48
     Би
    0.47
     nying
    0.47
     yü
    0.47
    POSITIVE LOGITS
    arrayOf
    0.48
    iral
    0.47
     unknowns
    0.47
     battleship
    0.46
    ixes
    0.45
     safely
    0.45
     प्रतीक्षा
    0.45
    gang
    0.44
     didn
    0.43
     মোতাবেক
    0.43
    Activations Density 0.000%

    No Known Activations