© 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. 70133
    Prev
    Next
    INDEX
    Explanations

    cooking and food descriptions

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

    delete everything after

    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
     重要
    0.57
    大学
    0.48
    ченный
    0.48
     大学
    0.48
     университе
    0.47
     教育
    0.47
    買取
    0.47
    蓥
    0.47
     болезнь
    0.47
     理解
    0.46
    POSITIVE LOGITS
     iklan
    0.46
     Rican
    0.45
     added
    0.44
     menu
    0.44
    fern
    0.44
     ameryka
    0.44
    apps
    0.43
     native
    0.42
     ad
    0.42
    native
    0.42
    Activations Density 0.000%

    No Known Activations