© 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. 156679
    Prev
    Next
    INDEX
    Explanations

    citations ending in semicolon

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

    Arcade Breakout, guanciale, pyrometry, ratios, razor

    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
    n
    0.51
     hydrogen
    0.46
     quarantine
    0.41
    joke
    0.41
     migration
    0.41
     convening
    0.41
    hydrogen
    0.40
     polypeptide
    0.40
     nucleons
    0.40
    凖
    0.40
    POSITIVE LOGITS
     verkrij
    0.48
     hãy
    0.47
     iskust
    0.47
     이는
    0.46
     Algunos
    0.45
     hablamos
    0.44
     Đây
    0.44
     mime
    0.43
     kurul
    0.43
     portes
    0.43
    Activations Density 0.001%

    No Known Activations