© 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. 137196
    Prev
    Next
    INDEX
    Explanations

    emotions and cognitive functions

    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
     resellers
    0.46
     reseller
    0.44
     recruiters
    0.39
    獾
    0.38
     publicit
    0.38
     cryptographic
    0.37
    гістра
    0.36
    鲳
    0.36
     blockchain
    0.35
     retailers
    0.35
    POSITIVE LOGITS
     personality
    0.68
    personality
    0.68
     emotional
    0.66
     emotions
    0.65
     Emotions
    0.61
     Personality
    0.57
     voluntary
    0.57
     भावनाओं
    0.57
    情绪
    0.56
    voluntary
    0.55
    Activations Density 0.048%

    No Known Activations