© 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. 224780
    Prev
    Next
    INDEX
    Explanations

    connection work database

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

    coordination and assistance

    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
     richly
    0.52
    prepare
    0.49
     discarding
    0.46
    isDisabled
    0.46
     homemade
    0.45
     faithfully
    0.45
    =[]
    0.44
     diligently
    0.44
    <unused86>
    0.44
    aabb
    0.44
    POSITIVE LOGITS
     договор
    0.51
     ayuda
    0.47
     구
    0.46
     место
    0.46
     conect
    0.46
     डायरे
    0.46
     песен
    0.45
     गुज
    0.45
     connecter
    0.44
     помога
    0.44
    Activations Density 0.000%

    No Known Activations