© 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. 20250
    Prev
    Next
    INDEX
    Explanations

    explore without

    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
    ；
    0.41
     lop
    0.40
    త్రిక
    0.39
    ignation
    0.39
    躯
    0.39
    orphan
    0.38
    strap
    0.38
     ,
    0.38
    ;
    0.38
    軻
    0.38
    POSITIVE LOGITS
    Efficiency
    0.45
     bragging
    0.44
     sensores
    0.44
    ँसी
    0.43
     पटाखे
    0.42
     করলেও
    0.41
    וי
    0.41
     solusi
    0.41
    仿佛
    0.41
    鱻
    0.40
    Activations Density 0.003%

    No Known Activations