© 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. 103141
    Prev
    Next
    INDEX
    Explanations

    subject followed by modal verb

    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
    required
    -1.19
    requirements
    -0.98
     saveurs
    -0.98
     стара
    -0.95
     coupé
    -0.95
     considera
    -0.94
    hever
    -0.94
    nically
    -0.91
     moza
    -0.90
     recens
    -0.90
    POSITIVE LOGITS
     should
    1.99
     need
    1.94
     must
    1.88
     can
    1.73
     cannot
    1.49
     has
    1.32
     needs
    1.25
     have
    1.23
     باید
    1.20
     должна
    1.17
    Activations Density 0.030%

    No Known Activations