© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28454
    Prev
    Next
    INDEX
    Explanations

    think or thinking variants

    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
     насо
    0.41
    헛
    0.40
     Бы
    0.39
    ूरिया
    0.39
     बुन्देलखण्ड
    0.37
     도움이
    0.37
     забо
    0.36
    伒
    0.36
    褔
    0.36
    Operand
    0.36
    POSITIVE LOGITS
     Think
    0.78
     think
    0.76
    Think
    0.72
    think
    0.70
     THINK
    0.66
     thinker
    0.63
     thinks
    0.60
     thinking
    0.56
     denke
    0.53
     denk
    0.51
    Activations Density 0.000%

    No Known Activations