© 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. 48257
    Prev
    Next
    INDEX
    Explanations

    technical documents and instructions

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

    GDScript, C#, JavaScript, CSS identifiers

    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
    uci
    0.44
    寧
    0.41
     deb
    0.39
     decrypt
    0.39
    на
    0.39
    ESA
    0.39
     ELECTRICAL
    0.38
    цион
    0.37
    нении
    0.37
     marginalised
    0.37
    POSITIVE LOGITS
     الملك
    0.49
     mại
    0.48
     سری
    0.48
     اثر
    0.47
    潴
    0.46
     犬
    0.45
    ihuahua
    0.44
     ആവശ്യ
    0.44
    dogs
    0.44
    indd
    0.43
    Activations Density 0.000%

    No Known Activations