© 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. 128737
    Prev
    Next
    INDEX
    Explanations

    midtown, everyday, off, site, constructions

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

    actual score or result

    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
    fru
    0.46
    玦
    0.45
    AppContext
    0.44
    请求
    0.44
    ^{+}$.
    0.43
    发起
    0.43
    лья
    0.43
    жин
    0.43
    許
    0.43
    жными
    0.42
    POSITIVE LOGITS
     उतरे
    0.48
    íte
    0.46
    enchymal
    0.46
     inoxid
    0.46
     Kuwait
    0.44
    icol
    0.43
     métallique
    0.43
     vigorously
    0.42
     coag
    0.42
    iolet
    0.41
    Activations Density 0.000%

    No Known Activations