© 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. 65924
    Prev
    Next
    INDEX
    Explanations

    function words and specific names

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

    certain words like "install"

    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
    舶
    0.51
    ovic
    0.48
    Historically
    0.46
     models
    0.44
     modelos
    0.44
    لقة
    0.44
    Models
    0.43
     profiles
    0.43
     Acts
    0.42
    ós
    0.42
    POSITIVE LOGITS
     szyb
    0.49
    տր
    0.47
     Buj
    0.46
    籟
    0.46
     जल्दी
    0.43
    টি
    0.43
     dziew
    0.42
    зой
    0.42
     correctamente
    0.41
     Borneo
    0.41
    Activations Density 0.000%

    No Known Activations