© 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. 36988
    Prev
    Next
    INDEX
    Explanations

    daily life activities

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

    technology and technical terms

    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
     уні
    0.50
     полное
    0.49
    applic
    0.48
     軍
    0.46
    ле
    0.46
     процессе
    0.45
     процесс
    0.45
     той
    0.44
     চট্ট
    0.44
     輸入
    0.43
    POSITIVE LOGITS
     Taliban
    0.53
     B
    0.50
     M
    0.46
     PV
    0.46
     cashback
    0.46
    Η
    0.46
     Kas
    0.45
     K
    0.45
    खम
    0.45
     sushi
    0.45
    Activations Density 0.000%

    No Known Activations