© 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. 173458
    Prev
    Next
    INDEX
    Explanations

    time, little, rate, coconut, level

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

    climate emergency, immediate issues, benefits

    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
    Ls
    0.45
    Schwarz
    0.44
    G
    0.44
    TW
    0.43
    TF
    0.43
     warships
    0.43
    8
    0.43
    7
    0.43
    TS
    0.42
     veneers
    0.42
    POSITIVE LOGITS
    ız
    0.53
    ྥ
    0.48
     सकती
    0.48
     लॉक
    0.46
    èrent
    0.45
     এন্ড
    0.45
    ूल
    0.45
     তাকিয়ে
    0.45
    েন
    0.44
    ında
    0.44
    Activations Density 0.000%

    No Known Activations