© 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. 116101
    Prev
    Next
    INDEX
    Explanations

    maps and graphs showing locations

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

    graph and network structures

    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
     দৃশ
    0.50
    麃
    0.48
     காட்சி
    0.47
     увеличения
    0.47
    噘
    0.47
     ड्रिल
    0.47
     দৃশ্য
    0.46
     뿐
    0.46
     المثلث
    0.45
     চৈ
    0.45
    POSITIVE LOGITS
     thereof
    0.49
     sus
    0.47
     UN
    0.47
     MIT
    0.46
     Rome
    0.46
     decided
    0.46
     collaboration
    0.45
     {
    0.45
     .
    0.44
     someone
    0.44
    Activations Density 0.000%

    No Known Activations