© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12572
    Prev
    Next
    INDEX
    Explanations

    technical terms and numbers

    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
    相
    0.41
    etragen
    0.39
     pressure
    0.38
     toucher
    0.38
    目
    0.38
     प्रेशर
    0.38
     barbit
    0.38
     വന്നു
    0.36
    량
    0.36
     ఉప
    0.35
    POSITIVE LOGITS
    Yaml
    0.45
     Sami
    0.43
    kir
    0.43
    Doctrine
    0.42
    ContactBundle
    0.41
     thème
    0.40
     Gallardo
    0.40
    尧
    0.39
    Crud
    0.39
     gc
    0.39
    Activations Density 0.003%

    No Known Activations