© 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. 146050
    Prev
    Next
    INDEX
    Explanations

    starts procuring data implementation

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

    ancient history and cultures

    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
    ്യ
    0.50
     clogged
    0.50
     junkie
    0.48
     cambiato
    0.47
     currentColor
    0.47
     goofy
    0.46
    ᱐
    0.46
     fantastical
    0.46
     রাজধান
    0.46
    miktar
    0.46
    POSITIVE LOGITS
     Begins
    0.50
     Nem
    0.47
    an
    0.47
     زمن
    0.46
    3
    0.45
     Boost
    0.45
     Lex
    0.44
     Starts
    0.44
     அதில்
    0.44
     Days
    0.43
    Activations Density 0.001%

    No Known Activations