© 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. 9077
    Prev
    Next
    INDEX
    Explanations

    your supplies

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

    idiomatic phrases

    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
    ья
    0.46
     оптими
    0.45
    圤
    0.45
    乐观
    0.44
    ལ
    0.43
     ঐক্য
    0.41
    Peace
    0.41
     רק
    0.41
    賊
    0.40
    卍
    0.40
    POSITIVE LOGITS
     sanitizer
    0.44
     brochures
    0.42
     disposable
    0.42
     consumables
    0.41
    aceutical
    0.41
     dédiée
    0.41
     dédié
    0.41
     pharmaceutical
    0.41
     vending
    0.41
     spô
    0.40
    Activations Density 0.000%

    No Known Activations