© 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. 75664
    Prev
    Next
    INDEX
    Explanations

    no deficiencies

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

    generate download options

    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
    Negative Logits
    thema
    0.53
    臀
    0.50
    ❼
    0.50
    管控
    0.50
    醜
    0.49
    ０
    0.49
    リスク
    0.48
    काता
    0.47
    পাশের
    0.47
    ⏱
    0.46
    POSITIVE LOGITS
     availability
    0.54
     cyberspace
    0.52
     golf
    0.50
     alkaline
    0.50
     Ernie
    0.50
     grouse
    0.50
     someplace
    0.50
     Dave
    0.50
     avail
    0.50
     pilot
    0.50
    Activations Density 0.002%

    No Known Activations