© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2198
    Prev
    Next
    INDEX
    Explanations

    psycho followed by therapy or analysis

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

    This neuron activates on occurrences of the prefix “psycho” (as in psychoeducational, psychoactive, psychoanalytic, psychotic, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.76
    </strong>
    -0.74
     تس
    -0.72
     πρό
    -0.71
    調子
    -0.70
    me
    -0.68
     нова
    -0.67
     квадра
    -0.67
    typically
    -0.67
     científica
    -0.67
    POSITIVE LOGITS
    Psych
    0.96
    Wiener
    0.96
     психо
    0.89
     baud
    0.87
     ActiveX
    0.86
    beria
    0.86
     Cik
    0.86
     Mantis
    0.85
     Somaliland
    0.84
    𝚡
    0.84
    Activations Density 0.023%

    No Known Activations