© 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. 59841
    Prev
    Next
    INDEX
    Explanations

    daily, monthly, or yearly plans

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

    Character creation

    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
    стом
    0.47
     limiter
    0.47
    ג
    0.47
    ё
    0.46
    strument
    0.46
     versatile
    0.46
    ום
    0.46
     g
    0.45
    izan
    0.44
     blizzard
    0.44
    POSITIVE LOGITS
     Nuestros
    0.55
     rằng
    0.54
     amerikan
    0.52
     Amerikan
    0.51
     néhány
    0.51
     ngồi
    0.49
     uygul
    0.49
     Endocr
    0.49
     Ashken
    0.49
     ដើម្បី
    0.48
    Activations Density 0.000%

    No Known Activations