© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    marketformreads

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

    muscle weakness, following rule, larger-sized

    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
    佲
    0.51
    Paciente
    0.50
    を変
    0.50
     Física
    0.49
    Crist
    0.49
    Arsenal
    0.49
    ｹ
    0.48
    𝗡
    0.48
    Lista
    0.48
     кеңсесинде
    0.48
    POSITIVE LOGITS
     cloves
    0.57
    0.54
     cinnamon
    0.52
     peasant
    0.51
     محاسبه
    0.50
     промышлен
    0.49
     pickled
    0.49
     ku
    0.49
     megs
    0.49
     infotainment
    0.49
    Activations Density 0.000%

    No Known Activations