© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    sales, materials, physics, policies, death, agricultural

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

    specific concepts and their implementation

    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
    溂
    0.49
    立马
    0.47
    赶紧
    0.46
     दिखाता
    0.46
    门口
    0.44
     включают
    0.44
     ওভারে
    0.44
     Baumann
    0.43
     кнопку
    0.43
    𝐺
    0.43
    POSITIVE LOGITS
     psychotherapy
    0.52
     antitumor
    0.50
    otherapeutic
    0.47
     andre
    0.46
     industrialized
    0.46
     agus
    0.45
     regenerative
    0.45
     sogen
    0.45
     desarrollando
    0.44
     &/
    0.44
    Activations Density 0.016%

    No Known Activations