© 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. 41002
    Prev
    Next
    INDEX
    Explanations

    providing service, support, and advice

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

    expressive attributes

    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
    ayani
    0.41
    ోధ
    0.39
    山市
    0.38
    ଭ
    0.38
     SUCCESSFULLY
    0.38
    幔
    0.38
     voldo
    0.38
    ूबी
    0.38
    ज्
    0.37
     Hopl
    0.36
    POSITIVE LOGITS
     Express
    0.41
     DG
    0.40
     Style
    0.39
    classe
    0.38
     Macht
    0.38
     fender
    0.37
    電流
    0.37
     É
    0.36
     Fact
    0.36
     Commander
    0.36
    Activations Density 0.004%

    No Known Activations