© 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. 60224
    Prev
    Next
    INDEX
    Explanations

    terms for

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

    rate, long, Simplify, Company, work, written, Density

    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
    ِي
    0.43
     vytvá
    0.43
     vulve
    0.42
     marcada
    0.41
     nécess
    0.41
     kte
    0.41
    ;,
    0.40
    माम
    0.40
    лизи
    0.40
     vyu
    0.40
    POSITIVE LOGITS
     tidy
    0.45
    勋
    0.44
    枝
    0.41
    次回
    0.41
    ด
    0.41
    smoothing
    0.39
    oung
    0.39
    นะครับ
    0.39
    interesting
    0.38
    top
    0.38
    Activations Density 0.000%

    No Known Activations