© 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. 113742
    Prev
    Next
    INDEX
    Explanations

    reports, instance, presentation, experts, sent, Islands

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

    health, lives, taskId

    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
    笥
    0.52
     పోటీ
    0.47
     વ્ય
    0.47
     уеннары
    0.47
     ফো
    0.47
     ប៉ុ
    0.47
     Букмекерская
    0.46
     પરંતુ
    0.46
     MARKETING
    0.46
     тексту
    0.46
    POSITIVE LOGITS
     trouv
    0.49
     onion
    0.45
     speedy
    0.43
    즙
    0.43
    ædia
    0.42
     documents
    0.41
     forceful
    0.41
     evidence
    0.40
     bishop
    0.40
     scientist
    0.40
    Activations Density 0.000%

    No Known Activations