© 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. 130520
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    handling lists and placeholders

    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
    quat
    0.47
    und
    0.45
    Comparator
    0.45
     empieza
    0.45
    ieu
    0.43
     valuation
    0.43
     سلمان
    0.43
    å
    0.43
     evaluates
    0.43
    ingu
    0.42
    POSITIVE LOGITS
    ج
    0.66
    گ
    0.52
    πί
    0.52
    tsó
    0.50
    нце
    0.50
     án
    0.48
     обстанов
    0.47
    پ
    0.47
     Lank
    0.47
     Sở
    0.47
    Activations Density 0.000%

    No Known Activations