© 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. 97071
    Prev
    Next
    INDEX
    Explanations

    garlic and arm

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

    explaining with imaginati

    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
    鵲
    0.53
    assoc
    0.51
    舶
    0.46
    來自
    0.46
    atgu
    0.46
    wchar
    0.46
    Sonar
    0.45
    واه
    0.44
    䡛
    0.44
    ूनी
    0.44
    POSITIVE LOGITS
     ihtiyaç
    0.47
     faint
    0.47
     Appel
    0.46
     Бай
    0.46
     Бон
    0.46
     Entscheid
    0.46
     fique
    0.45
     October
    0.45
     evolving
    0.45
     Revis
    0.45
    Activations Density 0.001%

    No Known Activations