© 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. 45255
    Prev
    Next
    INDEX
    Explanations

    certainty

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

    std::cout to console

    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
    i
    0.57
    0.55
    ↵
    0.54
    he
    0.54
    e
    0.54
    -
    0.54
    ü
    0.54
    ​
    0.54
    il
    0.52
    as
    0.52
    POSITIVE LOGITS
     đế
    0.51
     venezolano
    0.51
     지난해
    0.51
    椛
    0.51
     señaló
    0.50
    𒉣
    0.50
     vecchia
    0.49
     conclusão
    0.48
     seguida
    0.48
     pcMove
    0.48
    Activations Density 0.000%

    No Known Activations