© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 118917
    Prev
    Next
    INDEX
    Explanations

    quantifiable numbers and mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㭐
    0.41
    리
    0.40
    acariy
    0.39
    醝
    0.39
    濫
    0.38
    ریس
    0.38
    erende
    0.38
    anées
    0.38
    基础
    0.37
    ⟫
    0.37
    POSITIVE LOGITS
     number
    0.62
    number
    0.54
     liczba
    0.51
     नंबर
    0.50
     عدد
    0.49
     संख्या
    0.49
     patterns
    0.48
     число
    0.47
     millions
    0.46
     Millions
    0.45
    Activations Density 0.005%

    No Known Activations