© 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. 31-GEMMASCOPE-2-RES-262K
    7. 18986
    Prev
    Next
    INDEX
    Explanations

    composite material, press flower, weather forecasting

    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_31_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
    س
    0.64
     swimsuit
    0.56
    s
    0.55
     underwear
    0.53
     Course
    0.50
    e
    0.48
     toiletries
    0.48
     toilet
    0.48
    OE
    0.48
    guesses
    0.47
    POSITIVE LOGITS
     này
    0.50
     lợi
    0.50
    ૂર્ણ
    0.49
     vantagens
    0.47
    这个
    0.45
    べて
    0.45
     çıkan
    0.45
    ﻫ
    0.45
    λι
    0.45
    λης
    0.44
    Activations Density 0.001%

    No Known Activations