© 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. 83558
    Prev
    Next
    INDEX
    Explanations

    sponsored event

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

    -ish, Row, Book, Nag

    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
    ྥ
    0.52
     cylindrical
    0.49
    ضة
    0.49
    мата
    0.48
    Aluminum
    0.48
    ্লো
    0.48
    tahun
    0.47
    стта
    0.47
    সিদ্ধ
    0.47
    ικούς
    0.46
    POSITIVE LOGITS
     abs
    0.52
     Software
    0.48
     Ms
    0.48
     Research
    0.47
     Newsletter
    0.47
     優
    0.46
     Enterprise
    0.46
     اق
    0.46
    噁
    0.46
     Status
    0.45
    Activations Density 0.001%

    No Known Activations