© 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. 84431
    Prev
    Next
    INDEX
    Explanations

    aesthetic

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

    conclude with

    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
    ओं
    0.44
     weitere
    0.43
    彥
    0.43
     הל
    0.42
     повышение
    0.42
     interessante
    0.41
    ériment
    0.41
    CONSTANT
    0.41
     hohe
    0.41
     влияние
    0.41
    POSITIVE LOGITS
    ın
    0.46
     рада
    0.45
    <.
    0.43
     currentPage
    0.43
    country
    0.43
    பால்
    0.43
    ınızı
    0.42
    ନ୍ଦ
    0.42
     prochain
    0.42
     simply
    0.42
    Activations Density 0.000%

    No Known Activations