© 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. 138247
    Prev
    Next
    INDEX
    Explanations

    choice, decision, results, approval

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

    Greek yogurt, pipeline support, Popcorn

    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
     העולם
    0.55
    פות
    0.49
     ადგილ
    0.48
     নির্বাচন
    0.46
    FBSDKAccessToken
    0.46
    🌇
    0.46
     มุม
    0.46
    DeleteDialogOpen
    0.45
    版权
    0.45
    ױ
    0.45
    POSITIVE LOGITS
     hijos
    0.49
     Laundry
    0.46
     filhos
    0.45
     Medication
    0.43
     lavado
    0.43
     preventative
    0.43
     धोने
    0.43
     Moisture
    0.42
     že
    0.42
     renforc
    0.42
    Activations Density 0.003%

    No Known Activations