© 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. 132169
    Prev
    Next
    INDEX
    Explanations

    proclaim Freedom

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

    Trending, Specific, video

    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
     deterioration
    0.48
    ASON
    0.48
    ้ม
    0.48
    ΕΣ
    0.48
    Շ
    0.46
    degenerative
    0.46
    Diffusion
    0.45
     tablecloth
    0.45
    Auto
    0.44
    انگ
    0.43
    POSITIVE LOGITS
     이하
    0.46
     alo
    0.45
    鲨
    0.45
    weil
    0.44
    ᶦ
    0.44
    æg
    0.43
     proclaim
    0.43
     எ
    0.42
     बेहत
    0.42
     Photoc
    0.41
    Activations Density 0.000%

    No Known Activations