© 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. 87234
    Prev
    Next
    INDEX
    Explanations

    medals, ranks, scores

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

    generally or often

    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
     ഇപ്പോ
    0.43
    亮相
    0.41
     поскольку
    0.40
    vercel
    0.40
     अत्याधुनिक
    0.40
    www
    0.40
     www
    0.38
    臉
    0.38
     Cz
    0.38
     ರೂ
    0.38
    POSITIVE LOGITS
    Above
    0.48
    ሁሉም
    0.46
     lagen
    0.42
    anje
    0.42
     interrelated
    0.41
    (/^
    0.40
     والع
    0.40
    ിയും
    0.40
    putable
    0.40
    etar
    0.39
    Activations Density 0.001%

    No Known Activations