© 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. 238919
    Prev
    Next
    INDEX
    Explanations

    modules and flares

    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
    丼
    0.48
     polymorphism
    0.45
    حة
    0.45
     superhero
    0.45
     homeowner
    0.44
    📋
    0.44
    槨
    0.44
    桌面
    0.43
     hairpin
    0.43
    NCIA
    0.43
    POSITIVE LOGITS
    such
    0.49
     cenderung
    0.47
    supporters
    0.46
     อาท
    0.45
    akers
    0.44
    till
    0.44
    carriers
    0.44
    cosec
    0.44
     Такие
    0.43
     устройств
    0.43
    Activations Density 0.000%

    No Known Activations