© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54050
    Prev
    Next
    INDEX
    Explanations

    psychotherapy, counselling, therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     socialization
    -0.89
    IRB
    -0.77
     Morgen
    -0.77
     Monti
    -0.77
     كوم
    -0.76
    flag
    -0.76
     типи
    -0.76
    vania
    -0.75
    Flag
    -0.75
    sten
    -0.75
    POSITIVE LOGITS
     psychotherapy
    0.92
     Psychotherapy
    0.85
     counselling
    0.81
     liệu
    0.80
     Integrative
    0.78
     therapy
    0.77
    Coun
    0.76
     confidentialité
    0.75
     client
    0.75
     supervise
    0.75
    Activations Density 0.016%

    No Known Activations