© 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. 82990
    Prev
    Next
    INDEX
    Explanations

    outsourcing and crowdsourcing

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

    explaining concepts and requirements

    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
    Questa
    0.45
    Warnings
    0.44
    较大
    0.43
    asında
    0.43
    ന്നി
    0.41
    本书
    0.41
    较大的
    0.40
    Х
    0.40
     न्यूयॉर्क
    0.40
    యంలో
    0.39
    POSITIVE LOGITS
     একমাত্র
    0.47
     meaning
    0.46
     viability
    0.46
     workforce
    0.44
     どう
    0.44
    meaning
    0.43
     obviously
    0.42
     mustn
    0.42
     pesky
    0.41
     ಮಾತ್ರ
    0.41
    Activations Density 0.002%

    No Known Activations