© 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. 118047
    Prev
    Next
    INDEX
    Explanations

    liability whatsoever

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

    holding niche devices

    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
    ่
    0.51
    ัน
    0.50
    '
    0.48
    ни
    0.48
    豺
    0.48
    о
    0.46
    驾驶
    0.45
    结构
    0.45
    อิน
    0.43
    فع
    0.43
    POSITIVE LOGITS
     contemplating
    0.51
     Фургала
    0.51
     grumpy
    0.51
     extrapolate
    0.50
    risch
    0.50
    testimonial
    0.49
     construe
    0.49
     früheren
    0.48
     arise
    0.48
     stereotyp
    0.48
    Activations Density 0.000%

    No Known Activations