© 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. 187771
    Prev
    Next
    INDEX
    Explanations

    my pocket notebook

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

    instructions, "request", or "exit"

    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
    <0x89>
    0.52
     акции
    0.49
    '.
    0.49
    ый
    0.48
    砰
    0.47
    <0x87>
    0.47
    selectbox
    0.46
    <0x8A>
    0.46
    黨
    0.45
    珢
    0.45
    POSITIVE LOGITS
    _____
    0.51
    F
    0.51
    M
    0.49
    en
    0.48
    ____
    0.48
     صدی
    0.47
    ______
    0.47
     _______
    0.46
    aw
    0.46
     مثل
    0.45
    Activations Density 0.000%

    No Known Activations