© 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. 154340
    Prev
    Next
    INDEX
    Explanations

    address, duration, or equipment details

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

    language and specific terms

    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
     (^{
    0.52
     儿童
    0.52
    TreeNavigator
    0.50
     Straßen
    0.48
     न्यूयॉर्क
    0.47
     美国
    0.46
    杫
    0.46
     Surrounded
    0.45
    Ỹ
    0.45
     AVENUE
    0.45
    POSITIVE LOGITS
    住所
    0.51
     pertin
    0.50
     degust
    0.47
    ibility
    0.45
    わかり
    0.44
    弊
    0.43
    初めて
    0.43
    ляем
    0.43
     lordship
    0.42
     unpleasant
    0.42
    Activations Density 0.001%

    No Known Activations