© 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. 2105
    Prev
    Next
    INDEX
    Explanations

    psychology, cognition, and biases

    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
    enamefont
    0.44
    rawy
    0.43
    emde
    0.43
    aaS
    0.42
    mittal
    0.42
     സേ
    0.41
    吨
    0.40
    鎬
    0.39
     ট্রেক
    0.39
     sparsebundle
    0.39
    POSITIVE LOGITS
     psychology
    1.75
     psychological
    1.67
     psychologists
    1.65
     Psychology
    1.60
    心理
    1.59
     psychologist
    1.57
     Psychological
    1.52
     psychologically
    1.52
     neuropsych
    1.50
     psicología
    1.49
    Activations Density 0.065%

    No Known Activations