© 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. 195516
    Prev
    Next
    INDEX
    Explanations

    specialized terminology

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

    often after is

    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
    тному
    0.44
     phenolic
    0.43
    Ổ
    0.43
     turpentine
    0.42
    bereitung
    0.42
     kiosk
    0.42
     polyvinyl
    0.41
    Ỏ
    0.41
    Gaz
    0.41
     liberal
    0.40
    POSITIVE LOGITS
     क्वेश्चंस
    0.48
     खेलों
    0.47
     दावे
    0.46
    剜
    0.46
     inglês
    0.46
    钙
    0.45
    愆
    0.45
    y
    0.45
    เกม
    0.44
     Caesars
    0.44
    Activations Density 0.001%

    No Known Activations