© 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. 160344
    Prev
    Next
    INDEX
    Explanations

    conductivity obtained

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

    sometimes help

    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
     канторы
    0.49
     geniuses
    0.48
     ressources
    0.47
     उल्लेखनीय
    0.47
     որ
    0.46
     тър
    0.46
     piety
    0.45
    婶
    0.44
    ಜನ
    0.44
    𝚂
    0.44
    POSITIVE LOGITS
     Guides
    0.47
    HOST
    0.46
     Applicable
    0.45
     Association
    0.45
     Everyone
    0.44
    ize
    0.44
     The
    0.44
     Mode
    0.44
     Posted
    0.44
     Worldwide
    0.44
    Activations Density 0.004%

    No Known Activations