© 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. 196544
    Prev
    Next
    INDEX
    Explanations

    time, numbers, and measurable quantities

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

    negation or condition

    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
    的结果
    0.42
     innych
    0.42
     hasilnya
    0.41
    সাম্প্র
    0.41
    眄
    0.41
    Dowell
    0.40
    贰百
    0.40
    <0x91>
    0.40
    lbrack
    0.40
    বিষ
    0.40
    POSITIVE LOGITS
     thinks
    0.43
     Soho
    0.37
    ‌ترین
    0.37
     realises
    0.36
    百貨
    0.36
    feeding
    0.35
     organising
    0.34
     begs
    0.34
     clothing
    0.34
    estate
    0.34
    Activations Density 0.000%

    No Known Activations