© 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. 32988
    Prev
    Next
    INDEX
    Explanations

    guys happen

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

    Sieve of Eratosthenes

    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
     veja
    0.42
    벽
    0.42
    ⌄
    0.42
    번
    0.42
     թվ
    0.41
    ляю
    0.41
    핍
    0.41
    팅
    0.41
     ilan
    0.40
    色は
    0.40
    POSITIVE LOGITS
    le
    0.51
     của
    0.50
    ère
    0.48
    da
    0.47
     of
    0.47
    ຂອງ
    0.47
    ga
    0.45
    这类
    0.45
    dus
    0.43
    所有
    0.43
    Activations Density 0.000%

    No Known Activations