© 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. 119252
    Prev
    Next
    INDEX
    Explanations

    attitudes, opinions, and beliefs

    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
    ,'\
    -0.90
     Incenti
    -0.89
     Critics
    -0.85
    begriff
    -0.84
     histor
    -0.84
     riun
    -0.83
    isSuccess
    -0.82
     holiness
    -0.82
    Historio
    -0.82
    :'',
    -0.82
    POSITIVE LOGITS
     attitudes
    2.17
     attitude
    1.80
     Attitudes
    1.52
     respondents
    1.48
     views
    1.34
     opinions
    1.34
     beliefs
    1.31
    titudes
    1.27
    attitude
    1.26
     belief
    1.22
    Activations Density 0.048%

    No Known Activations