© 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. 114738
    Prev
    Next
    INDEX
    Explanations

    regularly ask, star wont

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

    providing boundaries

    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
     (
    0.54
    (
    0.43
     ساعت
    0.42
     Lp
    0.42
     so
    0.42
    0.42
     polls
    0.41
     up
    0.40
    [])
    0.40
     doe
    0.40
    POSITIVE LOGITS
    嚩
    0.59
    فاف
    0.57
     inoxyd
    0.55
    लाव
    0.54
    চনার
    0.52
    itchie
    0.52
    gypte
    0.51
    থন
    0.50
    фа
    0.49
    法的
    0.49
    Activations Density 0.000%

    No Known Activations