© 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. 120329
    Prev
    Next
    INDEX
    Explanations

    test annotations and functions

    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
    the
    0.50
    𝑏
    0.48
     তব
    0.47
    𓂀
    0.47
     விநாயக
    0.46
    ાં
    0.45
     reducing
    0.45
     সমুদ্র
    0.44
     জল
    0.43
    秵
    0.43
    POSITIVE LOGITS
    ،
    0.50
     aktive
    0.43
    ולה
    0.40
     este
    0.40
     Kollegen
    0.40
    ，
    0.39
     Até
    0.39
    igo
    0.39
     inic
    0.39
     Inst
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.