© 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. 125450
    Prev
    Next
    INDEX
    Explanations

    purchase and availability

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

    recognizing states or scenarios

    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
    뮐
    0.59
    遒
    0.47
     комп
    0.45
    反对
    0.45
    譙
    0.45
    邳
    0.44
     uñas
    0.43
    痳
    0.43
     برد
    0.42
    易
    0.42
    POSITIVE LOGITS
    is
    0.55
    ----------------
    0.50
     ---------------
    0.47
     गाडी
    0.46
    ریٹر
    0.45
    ****************
    0.44
    ┌
    0.44
    ри
    0.43
     tain
    0.43
    ern
    0.43
    Activations Density 0.000%

    No Known Activations