© 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. 201827
    Prev
    Next
    INDEX
    Explanations

    technical specifications or document sections

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

    concepts and their descriptors

    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
    Pract
    0.47
    竜
    0.47
     мав
    0.46
    Omar
    0.46
    豪
    0.45
    منابع
    0.44
     அதிகரி
    0.44
     singh
    0.44
     തയ്യാ
    0.43
    试点
    0.43
    POSITIVE LOGITS
     تنت
    0.53
    ቹ
    0.47
    enet
    0.47
    ι
    0.45
     आटे
    0.44
    ely
    0.42
     ينت
    0.42
    MDEwOlJlcG
    0.42
    en
    0.42
    ernel
    0.42
    Activations Density 0.000%

    No Known Activations