© 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. 57099
    Prev
    Next
    INDEX
    Explanations

    phrases with specific dosages

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

    major in anything

    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
    ิร์
    0.49
    Func
    0.46
    institution
    0.45
     instituição
    0.45
    лся
    0.45
     함수
    0.44
    팎
    0.43
    ਸ਼ਨ
    0.43
    ิ
    0.43
     акчага
    0.43
    POSITIVE LOGITS
     अपेक्षाकृत
    0.52
     Wireless
    0.44
    </h2>
    0.44
     doubtless
    0.43
     Embrace
    0.43
    的重要性
    0.42
     phenylalanine
    0.40
     शायद
    0.39
     accumulate
    0.39
    准确
    0.39
    Activations Density 0.000%

    No Known Activations