© 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. 109216
    Prev
    Next
    INDEX
    Explanations

    domain, units, paradox, core

    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
    clean
    0.48
     clean
    0.47
     cleaned
    0.46
     Clean
    0.43
    cleaned
    0.41
    {}
    0.40
    干净
    0.40
    Clean
    0.40
    洗
    0.39
     WASH
    0.39
    POSITIVE LOGITS
    xF
    0.40
     এখনই
    0.39
    proguard
    0.37
     هنگ
    0.37
     connot
    0.37
    韶
    0.37
     haunts
    0.36
     pá
    0.36
     Sadler
    0.36
    rific
    0.36
    Activations Density 0.033%

    No Known Activations