© 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. 43764
    Prev
    Next
    INDEX
    Explanations

    hypnagogic state, chronic bronchitis

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

    s followed by noun

    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
    يط
    0.49
     بص
    0.49
    ქმ
    0.49
    叽
    0.49
     forstå
    0.47
     évolution
    0.47
     zmian
    0.47
     mě
    0.46
     पदक
    0.46
     compréhension
    0.45
    POSITIVE LOGITS
    k
    0.55
    ni
    0.48
    ////
    0.47
     ಸಮಯದಲ್ಲಿ
    0.46
    pkl
    0.46
    pageno
    0.45
    ‍♂️
    0.43
    pairwise
    0.42
    /////
    0.42
    cdot
    0.42
    Activations Density 0.000%

    No Known Activations