© 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. 127499
    Prev
    Next
    INDEX
    Explanations

    there before

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

    technology and offers

    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
    exp
    0.50
    ay
    0.48
     Cherokee
    0.48
    change
    0.47
    mob
    0.47
    group
    0.47
    :
    0.46
     groups
    0.46
    มากขึ้น
    0.46
    bn
    0.45
    POSITIVE LOGITS
     ನಾನು
    0.43
    प्रथम
    0.43
    之类的
    0.43
     يكون
    0.41
    𒆜
    0.41
     నేను
    0.41
     PURCHASE
    0.41
    实行
    0.40
    ('').
    0.40
     cuja
    0.40
    Activations Density 0.000%

    No Known Activations