© 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. 89754
    Prev
    Next
    INDEX
    Explanations

    others like

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

    what to search

    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
     ז
    0.49
     musée
    0.49
     prav
    0.48
     гром
    0.47
    ᱯ
    0.47
     சுதந்திர
    0.46
     solely
    0.45
    к
    0.45
     ჟ
    0.44
     тот
    0.44
    POSITIVE LOGITS
    的部分
    0.48
    进行的
    0.45
     टिप्स
    0.43
    horizontalLayout
    0.43
     Aeonium
    0.43
     Dear
    0.42
    ارين
    0.42
    变化的
    0.42
     Growing
    0.42
     Benton
    0.41
    Activations Density 0.001%

    No Known Activations