© 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. 83833
    Prev
    Next
    INDEX
    Explanations

    copyright and advisors

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

    offering resources and information

    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
     当然
    0.49
     Sort
    0.45
     Albion
    0.45
     Bounty
    0.44
     زیر
    0.44
    🍪
    0.44
    举报
    0.43
    ‪‬
    0.43
     Blogging
    0.43
     Animal
    0.43
    POSITIVE LOGITS
     neoplasms
    0.61
     kinemat
    0.55
     neoplas
    0.52
     coagulation
    0.52
     cyclohexane
    0.51
     curvatures
    0.51
     formulae
    0.50
     enhancing
    0.50
     cylinders
    0.48
     hematopoietic
    0.48
    Activations Density 0.012%

    No Known Activations