© 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. 64652
    Prev
    Next
    INDEX
    Explanations

    pockets and storage for items

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

    pockets and carrying essential items

    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
     контей
    0.54
     Drawer
    0.50
    箱
    0.48
     мебели
    0.48
     suitcases
    0.48
     पैकिंग
    0.47
     melamine
    0.47
    Drawer
    0.47
     wardrobes
    0.46
     показали
    0.46
    POSITIVE LOGITS
     ISP
    0.48
     Fist
    0.46
    冤
    0.43
     State
    0.41
    Interpreter
    0.41
     ISR
    0.40
     server
    0.40
     scanner
    0.39
     Discord
    0.39
     Morse
    0.39
    Activations Density 0.045%

    No Known Activations