© 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. 183907
    Prev
    Next
    INDEX
    Explanations

    include dinners

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

    list items or 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
    tree
    0.44
    utani
    0.44
    someone
    0.44
    стре
    0.43
    กอง
    0.42
    Tree
    0.42
    重
    0.41
     Moh
    0.41
    vious
    0.41
    torn
    0.41
    POSITIVE LOGITS
    ₂)
    0.52
    ₁)
    0.49
     vingt
    0.49
     двадцать
    0.49
     méth
    0.48
     \|_{
    0.48
    ระหว่าง
    0.48
     அறிந்த
    0.48
     bár
    0.47
     américain
    0.46
    Activations Density 0.001%

    No Known Activations