© 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. 145053
    Prev
    Next
    INDEX
    Explanations

    religious, scientific, policy, or business contexts

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

    items listed after headings

    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
    i
    0.66
    ি
    0.52
    <0x80>
    0.46
     στα
    0.46
    ab
    0.44
     بينهم
    0.43
     weeping
    0.43
    ി
    0.43
    лении
    0.42
     нач
    0.42
    POSITIVE LOGITS
    冚
    0.48
    ní
    0.47
    奭
    0.46
    േക്ക്
    0.45
     antihy
    0.45
     Redox
    0.44
    वळ
    0.43
     äußerst
    0.43
     Reform
    0.43
    汜
    0.43
    Activations Density 0.000%

    No Known Activations