© 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. 84321
    Prev
    Next
    INDEX
    Explanations

    Hajj or errands

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

    genetic evidence, AMOLED, scale, ineffective

    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
    ृ
    0.41
    ⛲
    0.41
    PRODUCTS
    0.40
    恝
    0.40
     কয়েকটি
    0.40
     бесплатно
    0.39
    🏻
    0.39
    刑事
    0.38
    वय
    0.38
    ᐊ
    0.38
    POSITIVE LOGITS
     intermédiaire
    0.47
    iene
    0.46
     midday
    0.46
    他又
    0.46
    umo
    0.46
    centro
    0.45
     halftime
    0.44
     смо
    0.44
    core
    0.44
     isso
    0.43
    Activations Density 0.000%

    No Known Activations