© 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. 31-GEMMASCOPE-2-RES-262K
    7. 199600
    Prev
    Next
    INDEX
    Explanations

    start small and expand

    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
     svih
    0.47
    lf
    0.47
     Bukan
    0.46
     ->
    0.45
    oplay
    0.44
     entrou
    0.44
    ,
    0.44
     Nc
    0.43
    لان
    0.43
     empêcher
    0.43
    POSITIVE LOGITS
     คิด
    0.52
    คิด
    0.52
    мещение
    0.49
    MktCap
    0.48
    ాలలో
    0.47
    œur
    0.45
    細胞
    0.45
    দাস
    0.45
    ModelAndView
    0.44
    FindingsResponse
    0.44
    Activations Density 0.005%

    No Known Activations