© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18114
    Prev
    Next
    INDEX
    Explanations

    unfortunate combination or member companies

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

    avoid attempting

    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
    RO
    0.51
    let
    0.50
    இந்த
    0.49
    eight
    0.48
    five
    0.47
    メ
    0.47
    ３
    0.46
    八
    0.46
    新
    0.46
    ４
    0.46
    POSITIVE LOGITS
     Similarly
    0.49
     Deviation
    0.47
    同样的
    0.45
     व्यक्तियों
    0.43
     leurs
    0.42
     deviation
    0.42
     ঔষধ
    0.41
     მათი
    0.41
     마찬가지
    0.40
     trac
    0.40
    Activations Density 0.000%

    No Known Activations