© 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. 134791
    Prev
    Next
    INDEX
    Explanations

    foreign or other languages

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

    Be careful/mindful of time sinks

    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
     ખરી
    0.43
     lied
    0.43
     ଆ
    0.41
     محاضرت
    0.40
     عيد
    0.40
    ைகளும்
    0.39
    Ｇ
    0.39
    يات
    0.39
    味噌
    0.39
    ‼
    0.39
    POSITIVE LOGITS
    이나
    0.50
     või
    0.48
     navigable
    0.48
    あるいは
    0.47
     rôle
    0.47
     vitally
    0.46
    ,
    0.45
     secretory
    0.45
     yoki
    0.45
     of
    0.44
    Activations Density 0.003%

    No Known Activations