© 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. 182625
    Prev
    Next
    INDEX
    Explanations

    time sequences and contexts

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

    foreign punctuation and letters

    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
     hafa
    0.46
     f
    0.45
     yield
    0.43
     Oceania
    0.43
    л
    0.43
     produce
    0.42
     dip
    0.42
     ROG
    0.42
     type
    0.42
     use
    0.41
    POSITIVE LOGITS
    宴
    0.48
    监督
    0.48
    同事
    0.47
    јединачна
    0.47
     মুক্তিফৌজ
    0.46
     თ
    0.45
    行的
    0.45
    핞
    0.45
    斉
    0.45
    τια
    0.44
    Activations Density 0.001%

    No Known Activations