© 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. 183339
    Prev
    Next
    INDEX
    Explanations

    eternal and distinguished concepts

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

    dealing with topics

    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
     naro
    0.49
    Მ
    0.46
     walaupun
    0.45
    Surgery
    0.45
    Grim
    0.44
     উপলব্ধ
    0.44
    ÉRI
    0.44
     ත
    0.44
     Ching
    0.44
     například
    0.43
    POSITIVE LOGITS
     eternal
    0.55
     πως
    0.54
     distinguished
    0.53
    at
    0.50
     eterno
    0.50
     insidious
    0.49
     metamorphosis
    0.48
     infallible
    0.48
     abolished
    0.48
    apsing
    0.48
    Activations Density 0.001%

    No Known Activations