© 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. 26275
    Prev
    Next
    INDEX
    Explanations

    context and attributes

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

    knowing that

    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
     heuristics
    0.39
    嚶
    0.39
     mse
    0.38
     diverses
    0.37
     xylem
    0.36
    ικά
    0.36
     viens
    0.36
     Consensus
    0.35
    霖
    0.35
    같이
    0.35
    POSITIVE LOGITS
     knowing
    0.63
     Knowing
    0.61
    Knowing
    0.57
    knowing
    0.56
    有了
    0.46
    知道了
    0.45
     mengetahui
    0.44
     grâce
    0.43
    assured
    0.43
    supported
    0.42
    Activations Density 0.230%

    No Known Activations