© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30007
    Prev
    Next
    INDEX
    Explanations

    reporting internal thoughts

    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
    Negative Logits
     Suggest
    -0.90
     Suggestion
    -0.85
     दिख
    -0.84
     appetites
    -0.82
    García
    -0.80
     explications
    -0.79
    StringTokenizer
    -0.75
     Requested
    -0.75
    Suggest
    -0.75
    Suggestion
    -0.75
    POSITIVE LOGITS
     thought
    2.75
     thoughts
    2.03
     thinking
    2.02
     inwardly
    1.70
     internal
    1.66
    thought
    1.65
     internally
    1.61
     Thought
    1.58
     thinks
    1.57
    thinking
    1.57
    Activations Density 0.017%

    No Known Activations