© 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. 225890
    Prev
    Next
    INDEX
    Explanations

    helping clients

    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
    باً
    0.45
    lr
    0.43
    شي
    0.43
     嗯
    0.43
    inated
    0.43
    ̑
    0.42
    bah
    0.42
    偉
    0.42
    ти
    0.42
     rearrangements
    0.42
    POSITIVE LOGITS
     যেরূপ
    0.46
     wannan
    0.44
     bertanya
    0.44
     dossier
    0.43
     socalled
    0.43
     collabor
    0.42
     suivie
    0.42
     जाईल
    0.41
     ώστε
    0.41
     ပ
    0.41
    Activations Density 0.003%

    No Known Activations