© 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. 159873
    Prev
    Next
    INDEX
    Explanations

    patient's skin

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

    topics, trends, and time

    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
    لم
    0.53
    ल
    0.52
    л
    0.52
    u
    0.50
    مام
    0.46
    म
    0.46
    <blockquote>
    0.45
       
    0.45
    ت
    0.45
    पुस्तक
    0.44
    POSITIVE LOGITS
     demás
    0.49
     hairy
    0.48
     regenv
    0.48
     মসজি
    0.47
     Дар
    0.47
     Hawking
    0.47
     我们
    0.46
     unob
    0.46
     Nuestro
    0.46
    我們
    0.46
    Activations Density 0.000%

    No Known Activations