© 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. 47449
    Prev
    Next
    INDEX
    Explanations

    and , R Lafayette

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

    starting a question or action

    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
    ஷ
    0.42
     Riemannian
    0.41
     års
    0.41
     breit
    0.41
     freestyle
    0.40
     classically
    0.40
     pinched
    0.39
     Freestyle
    0.39
     salary
    0.38
     salaried
    0.38
    POSITIVE LOGITS
    អស់
    0.49
     લગભગ
    0.48
    VRDR
    0.48
     молока
    0.48
     després
    0.47
    𝗨
    0.47
    daughters
    0.46
     praticamente
    0.46
    狀況
    0.46
    bacteria
    0.45
    Activations Density 0.000%

    No Known Activations