© 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. 239760
    Prev
    Next
    INDEX
    Explanations

    writing, patent, flying, cancer, long-term relationship

    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
     பார்
    0.58
    consider
    0.48
    পত্র
    0.48
    newsletter
    0.48
    კ
    0.48
     প্রসার
    0.47
     ምክንያት
    0.47
     সাত
    0.46
    佔
    0.46
    networking
    0.46
    POSITIVE LOGITS
     incompatibility
    0.55
    वले
    0.51
     Usa
    0.50
    िशा
    0.49
     EEUU
    0.48
     repulsion
    0.48
     individ
    0.48
     restit
    0.48
     britt
    0.47
     volv
    0.47
    Activations Density 0.000%

    No Known Activations