© 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. 195224
    Prev
    Next
    INDEX
    Explanations

    past updates, often overlooked, signifies maturity

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

    advanced systems and data structures

    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
    Sit
    0.46
     Servicios
    0.45
    ANY
    0.42
     বিন্দু
    0.41
     ٿ
    0.41
    體
    0.41
     oversee
    0.41
    Sig
    0.40
     ডাকে
    0.40
    靚
    0.40
    POSITIVE LOGITS
    nnet
    0.50
    䪱
    0.49
    AvlTree
    0.49
    nacht
    0.48
    rangea
    0.48
    คองโก
    0.47
    ambuco
    0.47
    وة
    0.46
    ową
    0.46
    ामो
    0.46
    Activations Density 0.000%

    No Known Activations