© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127944
    Prev
    Next
    INDEX
    Explanations

    technical online information jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дам
    0.51
    .|__
    0.50
     הר
    0.49
     रोटी
    0.48
     دنبال
    0.48
     શ્રી
    0.47
     المطلوب
    0.47
    ﭜ
    0.47
    ຂອງ
    0.47
     금융
    0.46
    POSITIVE LOGITS
     a
    0.52
     diagon
    0.47
     Prok
    0.46
     técnicos
    0.44
     Brahmin
    0.43
     separados
    0.43
    ल्ल्या
    0.42
     BMD
    0.41
     comprov
    0.40
    嵋
    0.40
    Activations Density 0.003%

    No Known Activations