© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173890
    Prev
    Next
    INDEX
    Explanations

    association testimonials

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

    research areas, scientific reasoning, parts

    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
     ರೀತಿಯ
    0.50
     అలాగే
    0.49
     پرورش
    0.48
    ieh
    0.48
    systems
    0.45
    భర
    0.45
     வரைய
    0.45
    楍
    0.44
     رشته
    0.44
     राहणार
    0.43
    POSITIVE LOGITS
     detectives
    0.56
    <?
    0.52
     time
    0.51
    时间
    0.51
     wm
    0.49
     expectations
    0.48
    후
    0.47
    '
    0.47
     separat
    0.46
     firefighter
    0.46
    Activations Density 0.000%

    No Known Activations