© 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. 82932
    Prev
    Next
    INDEX
    Explanations

    too followed by intensifiers

    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
    somewhat
    -1.30
     fotografi
    -1.30
    oit
    -1.30
    almost
    -1.25
     somewhat
    -1.24
    
    -1.24
     juſ
    -1.21
     vna
    -1.20
     biografi
    -1.19
     薬局
    -1.16
    POSITIVE LOGITS
     much
    1.66
     many
    1.54
     often
    1.52
     difficult
    1.41
     terribly
    1.36
     different
    1.36
     important
    1.30
     dissimilar
    1.27
    Many
    1.23
    Unlike
    1.23
    Activations Density 0.011%

    No Known Activations