© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    your contacts

    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
    :
    0.19
     =
    0.19
     abscess
    0.18
     زاده
    0.18
     creatine
    0.18
    -
    0.18
    =")
    0.17
     :
    0.17
     arginine
    0.17
     dystrophy
    0.17
    POSITIVE LOGITS
     déclar
    0.21
    Ბ
    0.21
    闗
    0.21
    䛛
    0.21
     बोझ
    0.20
    菣
    0.20
     nyelv
    0.20
    霝
    0.20
    孱
    0.20
    ản
    0.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.