© 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. 74127
    Prev
    Next
    INDEX
    Explanations

    specific entities and continuations

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

    understanding why

    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
     মানে
    0.53
     ма
    0.47
     Ginkuhà
    0.46
     экрана
    0.46
    മുണ്ട
    0.46
     લ
    0.45
     ከፍተኛ
    0.45
     માર
    0.44
     ትንሽ
    0.43
     हाइड्र
    0.43
    POSITIVE LOGITS
    ോഷ
    0.54
    duty
    0.50
    t
    0.49
     contexts
    0.48
     Duty
    0.46
     OSI
    0.45
    have
    0.45
     Time
    0.44
     DUT
    0.44
     ToString
    0.44
    Activations Density 0.000%

    No Known Activations