© 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. 14888
    Prev
    Next
    INDEX
    Explanations

    know that

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

    knowing or not knowing

    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
    ج
    0.77
    ش
    0.70
    <0x0D>
    0.66
    م
    0.63
    кту
    0.62
    ك
    0.62
    গ্র
    0.61
    0.61
     elenco
    0.59
    ব্র
    0.59
    POSITIVE LOGITS
    의
    0.75
    ır
    0.73
     که
    0.69
     as
    0.68
     about
    0.66
     bahwa
    0.66
    lege
    0.64
     oleh
    0.64
    ه‌های
    0.64
    _
    0.63
    Activations Density 0.104%

    No Known Activations