© 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. 107354
    Prev
    Next
    INDEX
    Explanations

    Olympic, infographic, away

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

    official disclaimer

    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
     AcOH
    0.55
     In
    0.53
    ر
    0.49
    یسی
    0.49
     Kada
    0.49
    In
    0.48
    ר
    0.48
     BOOKS
    0.47
    ПК
    0.47
    AcOH
    0.47
    POSITIVE LOGITS
    fer
    0.49
    anya
    0.48
    rogens
    0.47
    ¼
    0.45
     ব্লক
    0.44
    ❃
    0.43
    ğim
    0.42
    ¾
    0.42
     ব্যক্তির
    0.42
    followlike
    0.42
    Activations Density 0.000%

    No Known Activations