© 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. 137143
    Prev
    Next
    INDEX
    Explanations

    waterproof, zest, read, combination, EE

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

    international audience

    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
     pruž
    0.46
     তথাপি
    0.45
     लेंस
    0.45
     možda
    0.45
     Imaging
    0.44
    нологи
    0.44
    𒅎
    0.44
    Imaging
    0.44
    сіі
    0.44
     Hills
    0.43
    POSITIVE LOGITS
    投稿
    0.47
     (
    0.46
    後
    0.45
     disposable
    0.45
    internal
    0.44
    互
    0.44
    邂
    0.43
    ut
    0.43
     Huz
    0.43
    冬
    0.43
    Activations Density 0.001%

    No Known Activations