© 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. 72599
    Prev
    Next
    INDEX
    Explanations

    that we

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

    bubble, ball, physics

    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
     descriptor
    0.47
    endente
    0.44
     প্রধানমন্ত্রীর
    0.44
    ichtet
    0.43
     видимо
    0.43
    ꯤ
    0.43
     soporte
    0.43
     बढ
    0.43
     hoog
    0.42
    ersonic
    0.42
    POSITIVE LOGITS
    Giá
    0.48
    Vend
    0.45
    冤
    0.43
    Ari
    0.42
    Bub
    0.42
    Sugar
    0.42
    ℞
    0.41
    Addr
    0.40
    Holiday
    0.40
     Bub
    0.40
    Activations Density 0.001%

    No Known Activations