© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8124
    Prev
    Next
    INDEX
    Explanations

    sorting optimization flag comments

    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_40_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
     पोशा
    0.48
     añadi
    0.47
    uisine
    0.46
     Quelle
    0.44
     религи
    0.44
    嗽
    0.43
    ेज
    0.42
     añadir
    0.42
     વિશે
    0.41
    惬
    0.41
    POSITIVE LOGITS
     organismo
    0.47
     traverse
    0.43
     effectively
    0.42
    elda
    0.41
     outer
    0.39
     observed
    0.39
    Army
    0.38
     গভর্নর
    0.37
     गवर्नर
    0.37
     seen
    0.37
    Activations Density 0.000%

    No Known Activations