© 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. 193202
    Prev
    Next
    INDEX
    Explanations

    arrangement

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

    technical details

    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
    ีย
    0.46
    antan
    0.41
     Utilize
    0.41
     Contributing
    0.41
    avorable
    0.40
    ា
    0.40
     Carpenter
    0.39
    ╗
    0.39
     Personally
    0.39
     إص
    0.39
    POSITIVE LOGITS
     mating
    0.50
     artery
    0.50
     montre
    0.47
     toeg
    0.47
     menonton
    0.46
     piatto
    0.46
     radiotherapy
    0.46
     langage
    0.46
    steppe
    0.46
     nome
    0.45
    Activations Density 0.004%

    No Known Activations