© 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. 103848
    Prev
    Next
    INDEX
    Explanations

    tribunal process, three times, had been

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

    concepts of measurement 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
    ‌,
    0.45
    კის
    0.42
    رض
    0.42
     இயக்கு
    0.42
    மொ
    0.41
     داخل
    0.40
     دیدار
    0.40
    焦
    0.40
     Announces
    0.40
    രക്ഷ
    0.39
    POSITIVE LOGITS
     ವ್ಯಾ
    0.52
     avven
    0.51
     valido
    0.51
     \$
    0.48
     persen
    0.46
     Prussian
    0.46
     שט
    0.45
     feito
    0.45
     corsi
    0.44
     \"%
    0.44
    Activations Density 0.011%

    No Known Activations