© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    qualifiers and descriptions

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

    describing attributes and connections

    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
     sdx
    0.42
     એક
    0.41
     său
    0.40
     ایک
    0.38
     isomorphisms
    0.38
    ⮚
    0.38
    వ్వ
    0.37
     一个
    0.37
     的
    0.37
     The
    0.36
    POSITIVE LOGITS
     requiring
    0.60
     featuring
    0.57
     containing
    0.56
     resembling
    0.56
    featuring
    0.54
     comprising
    0.54
     bordering
    0.50
     consisting
    0.49
     occurring
    0.49
     amounting
    0.49
    Activations Density 0.153%

    No Known Activations