© 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. 141627
    Prev
    Next
    INDEX
    Explanations

    materials, looking, license, powers, scrape

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

    consensual behavior, themes, KMS key

    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
     traitements
    0.49
    ण
    0.47
    車の
    0.46
    ბ
    0.46
     rechten
    0.46
     shootings
    0.46
    清水
    0.46
    嬬
    0.45
     nowego
    0.45
     excavations
    0.44
    POSITIVE LOGITS
    āk
    0.52
    ání
    0.50
     năng
    0.46
    াকারী
    0.46
     Quốc
    0.45
    omét
    0.44
    ění
    0.44
     hiển
    0.44
    avasena
    0.43
    oč
    0.42
    Activations Density 0.001%

    No Known Activations