© 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. 28442
    Prev
    Next
    INDEX
    Explanations

    artists, cars, events, offers

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

    evolutionary process

    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
    Sud
    0.49
    ésre
    0.49
    the
    0.44
    Somewhere
    0.43
    some
    0.43
    బ్ర
    0.43
    과
    0.42
    Pars
    0.41
    무
    0.41
    솔
    0.41
    POSITIVE LOGITS
     descuentos
    0.49
     isk
    0.47
     enshrined
    0.43
     اصلی
    0.43
     ہاتھوں
    0.42
     calligraphy
    0.42
     purest
    0.42
     espiritual
    0.42
    可以直接
    0.41
    ティーク
    0.41
    Activations Density 0.000%

    No Known Activations