© 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. 161684
    Prev
    Next
    INDEX
    Explanations

    in my

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

    constant changes

    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
    PSON
    0.50
     enfermedades
    0.49
    手
    0.49
     longitudinale
    0.48
    내
    0.48
    ادی
    0.47
    RELATES
    0.47
    نی
    0.47
    PSI
    0.47
    ذی
    0.47
    POSITIVE LOGITS
    Hide
    0.43
     teri
    0.42
     СО
    0.42
    ityanath
    0.42
    о
    0.41
     нанесе
    0.41
     አሉ
    0.40
     tig
    0.40
     стреми
    0.40
     feared
    0.39
    Activations Density 0.000%

    No Known Activations