© 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. 76936
    Prev
    Next
    INDEX
    Explanations

    software add-ons and plugins

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

    plugin or addon

    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
     userRepository
    0.42
    leftChild
    0.41
     grosseur
    0.40
     くれ
    0.40
     grandeza
    0.40
     লিখিতে
    0.39
     сн
    0.38
    쵝
    0.38
    bonne
    0.37
    டக
    0.37
    POSITIVE LOGITS
    插件
    0.98
     plugin
    0.97
     Plugin
    0.88
    Plugin
    0.80
    plugin
    0.77
     PLUGIN
    0.75
    PLUGIN
    0.72
     addon
    0.68
     plugins
    0.63
    プラグ
    0.63
    Activations Density 0.240%

    No Known Activations