© 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. 150518
    Prev
    Next
    INDEX
    Explanations

    celiac disease foundation trust

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

    html and xml parsing

    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
     Xinjiang
    0.46
     সংগ্রহ
    0.45
     हिस्से
    0.43
     miejscowości
    0.43
     collected
    0.42
     Negeri
    0.41
    舊
    0.41
    收集
    0.40
     Gann
    0.40
     तिथ
    0.39
    POSITIVE LOGITS
    grade
    0.44
    TAG
    0.40
    sels
    0.40
    hor
    0.39
     hor
    0.39
    Hor
    0.39
    paragraph
    0.39
    shorts
    0.38
    JW
    0.38
    Client
    0.38
    Activations Density 0.003%

    No Known Activations