© 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. 12985
    Prev
    Next
    INDEX
    Explanations

    relative paths/commands

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

    ./ followed by a command or file

    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
    타
    0.52
     नही
    0.51
     percent
    0.46
     sẽ
    0.46
     करेगा
    0.46
    ན་
    0.45
     gerenci
    0.45
     challenge
    0.44
     misuse
    0.44
    ཌ
    0.44
    POSITIVE LOGITS
    quatre
    0.48
     espèces
    0.45
    кра
    0.45
    gleichen
    0.45
    дный
    0.44
     waarom
    0.43
    يلي
    0.43
    ../
    0.42
    chir
    0.42
    سباب
    0.42
    Activations Density 0.003%

    No Known Activations