© 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. 143035
    Prev
    Next
    INDEX
    Explanations

    addition, also, necessary, switch, living

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

    zebra in lion country

    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
     Fujita
    0.57
    诙
    0.50
     Elemental
    0.50
     Promotional
    0.47
     Kohler
    0.45
    奀
    0.45
     hozzá
    0.44
    دانلود
    0.44
    ꫝ
    0.44
     Filmm
    0.43
    POSITIVE LOGITS
     impulses
    0.46
    input
    0.45
    GOD
    0.43
    ¸
    0.42
    вое
    0.42
    iov
    0.41
    ino
    0.40
    object
    0.40
    FRING
    0.40
     nigra
    0.40
    Activations Density 0.000%

    No Known Activations