© 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. 47268
    Prev
    Next
    INDEX
    Explanations

    receptacle placement and usage

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

    AI model sizes

    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
     spelled
    0.52
    َي
    0.47
    格外
    0.46
     Nummer
    0.46
    í
    0.46
    K
    0.43
     GUAR
    0.43
    v
    0.42
    ٍ
    0.42
    inated
    0.41
    POSITIVE LOGITS
     ultrason
    0.51
     fermionic
    0.50
    墺
    0.50
     системы
    0.49
     manor
    0.49
     unary
    0.48
     монасты
    0.48
    ানন্দ
    0.48
     кня
    0.47
     acids
    0.47
    Activations Density 0.000%

    No Known Activations