© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 175751
    Prev
    Next
    INDEX
    Explanations

    dates, professions, roles

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

    identifying forest types

    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
     عندما
    0.52
    ASTIC
    0.48
    OLOGICAL
    0.45
    IDI
    0.43
    ASTER
    0.43
    ERICAN
    0.43
    葦
    0.43
    anneled
    0.42
     foundation
    0.42
     ری
    0.41
    POSITIVE LOGITS
     encontra
    0.61
     SoC
    0.55
    찾
    0.55
    гах
    0.54
    활
    0.52
     encont
    0.51
    źć
    0.51
    benzoimidazole
    0.49
    껐
    0.48
     NodeRef
    0.47
    Activations Density 0.000%

    No Known Activations