© 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. 1031
    Prev
    Next
    INDEX
    Explanations

    living things and organizations

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

    life and living things

    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
    ：
    0.46
    component
    0.44
    ATE
    0.44
    Ｔ
    0.44
    ZE
    0.44
    mpeg
    0.43
    components
    0.42
    зи
    0.42
    Nag
    0.41
    ཥ
    0.41
    POSITIVE LOGITS
     existentes
    0.55
     ಅಥವಾ
    0.54
     أو
    0.54
     hoặc
    0.52
     كلهم
    0.52
     poput
    0.52
     ឬ
    0.49
     spores
    0.49
     অন্যদের
    0.48
     किंवा
    0.47
    Activations Density 0.012%

    No Known Activations