© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8786
    Prev
    Next
    INDEX
    Explanations

    psychoanalysis, psychotherapy, psychiatric

    np_acts-logits-general · gemini-2.5-flash-lite

    subconscious mind and psychology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    গ্রামী
    0.42
     иск
    0.42
     प्रवीण
    0.41
     शता
    0.41
     फस
    0.41
    鍗
    0.40
     ประก
    0.40
     DECL
    0.40
     ENGINEER
    0.39
    螻
    0.39
    POSITIVE LOGITS
     psycho
    1.80
     Freud
    1.75
     Psycho
    1.73
     psico
    1.44
    Psy
    1.42
     Sigmund
    1.30
    psy
    1.23
     psychotherapy
    1.23
     psychos
    1.13
     psych
    1.13
    Activations Density 0.153%

    No Known Activations