© 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. 155694
    Prev
    Next
    INDEX
    Explanations

    production and figures

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

    collect setting hit reply overgrown

    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
    ❤️❤️
    0.48
    amps
    0.46
    ytu
    0.46
     discontinuities
    0.46
    because
    0.45
     Directors
    0.45
    émon
    0.45
    inol
    0.44
    øm
    0.44
     refunds
    0.44
    POSITIVE LOGITS
    対訳
    0.49
    ี
    0.48
     موت
    0.48
    ญิง
    0.47
     уви
    0.46
     просмо
    0.45
     употреб
    0.45
    BackPressed
    0.44
     regexp
    0.44
    潙
    0.43
    Activations Density 0.001%

    No Known Activations