© 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. 112239
    Prev
    Next
    INDEX
    Explanations

    Facebook benchmarking tool

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

    molding on chip

    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
    רים
    0.48
    ໂດຍ
    0.45
    河南
    0.44
    ेशनों
    0.43
    就在
    0.42
     성공
    0.42
     Controversy
    0.42
    Ｃ
    0.41
     Requirements
    0.41
     Provident
    0.41
    POSITIVE LOGITS
     geométricas
    0.53
    }.
    0.50
    ')?.
    0.50
    eye
    0.50
     تحليل
    0.49
    =>{
    0.49
    }_{\
    0.48
     delimiter
    0.47
    し
    0.47
    indik
    0.47
    Activations Density 0.001%

    No Known Activations