© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 35957
    Prev
    Next
    INDEX
    Explanations

    gene editing or theological perspectives

    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_65k_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
    yarn
    0.45
    管
    0.44
     retinal
    0.42
    受益
    0.42
    ukat
    0.41
    h
    0.41
    ua
    0.41
    phobic
    0.41
    year
    0.40
    жек
    0.40
    POSITIVE LOGITS
     Slider
    0.57
     Groupon
    0.48
     ഇങ്ങനെ
    0.48
     Lov
    0.47
     Directory
    0.47
    邙
    0.46
     Dictionary
    0.45
    Slider
    0.45
     Lifestyle
    0.45
     thậm
    0.45
    Activations Density 0.020%

    No Known Activations