© 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. 188613
    Prev
    Next
    INDEX
    Explanations

    speech and language context

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

    PowerPoint breached blood glucose

    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
    d
    0.50
    discrete
    0.49
     aires
    0.47
     create
    0.47
    かけ
    0.46
    彪
    0.45
    لقة
    0.45
    s
    0.44
    挂
    0.44
    顶
    0.44
    POSITIVE LOGITS
    ISTRATION
    0.55
    itative
    0.52
    Png
    0.50
    ouville
    0.50
    Senha
    0.50
    鈾
    0.49
    Teacher
    0.49
    ంధ్ర
    0.48
     існу
    0.48
    <unused27>
    0.48
    Activations Density 0.000%

    No Known Activations