© 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-16K
    7. 11956
    Prev
    Next
    INDEX
    Explanations

    superlative quality material

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

    introduces code explanations

    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_16k_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
    いくつか
    0.58
    🙍
    0.58
     তেমন
    0.58
     sesuatu
    0.55
     morphism
    0.54
     sobretudo
    0.54
     少し
    0.54
     তরফে
    0.54
     metaphorical
    0.54
     overarching
    0.54
    POSITIVE LOGITS
     unsurpassed
    0.88
    !
    0.74
     fully
    0.70
    !!!
    0.68
     hundreds
    0.68
     Hundreds
    0.67
     superbly
    0.67
     सैकड़ों
    0.65
    Hundreds
    0.65
     cientos
    0.65
    Activations Density 0.921%

    No Known Activations