© 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. 99526
    Prev
    Next
    INDEX
    Explanations

    availability and status

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

    numbers and languages

    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
    逗
    0.54
    NG
    0.47
    刻
    0.46
    本地
    0.43
     unteren
    0.42
    Nh
    0.41
     اپنے
    0.41
     দলকে
    0.41
     corz
    0.41
    彻
    0.41
    POSITIVE LOGITS
    าราง
    0.48
    сподар
    0.46
    ंगत
    0.46
     Seorang
    0.45
     aantal
    0.44
    scanner
    0.43
    ್ಣ
    0.43
     seorang
    0.42
    মাপ
    0.42
     מספר
    0.41
    Activations Density 0.000%

    No Known Activations