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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insectes
    0.48
     tumeurs
    0.46
     intérêt
    0.46
     orchards
    0.45
     animaux
    0.44
     cogeneration
    0.43
     bungalows
    0.43
    嫐
    0.43
     rameaux
    0.42
     œufs
    0.42
    POSITIVE LOGITS
    //
    0.75
    is
    0.66
    (
    0.59
    _
    0.57
    {
    0.56
    let
    0.55
    "
    0.55
    $
    0.54
    0.54
    int
    0.50
    Activations Density 0.043%

    No Known Activations