© 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. 222898
    Prev
    Next
    INDEX
    Explanations

    non-English phrases

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

    instructions and actions

    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
    Az
    0.57
    Z
    0.56
    2
    0.55
    AP
    0.54
    L
    0.54
    MP
    0.52
    OP
    0.51
    1
    0.50
    AZ
    0.50
    Prison
    0.48
    POSITIVE LOGITS
     polyamide
    0.49
     빨
    0.48
     Jorg
    0.48
     لوگ
    0.47
    avacak
    0.44
     نیچے
    0.43
     solv
    0.43
     وک
    0.43
     فضای
    0.43
     오른
    0.42
    Activations Density 0.000%

    No Known Activations