© 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. 90620
    Prev
    Next
    INDEX
    Explanations

    social phobia

    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
     frustration
    -0.90
     _('
    -0.90
     Allegretto
    -0.88
     frustrated
    -0.87
     گی
    -0.78
     Regio
    -0.78
    Tired
    -0.76
     frustrate
    -0.76
     Antara
    -0.76
     XXVII
    -0.75
    POSITIVE LOGITS
     anxiety
    2.98
     Anxiety
    2.67
    Anxiety
    2.44
     phobia
    2.41
    anxiety
    2.30
     fear
    2.25
     panic
    2.17
     pho
    2.06
     anxious
    2.00
     Fear
    1.98
    Activations Density 0.076%

    No Known Activations