© 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. 54298
    Prev
    Next
    INDEX
    Explanations

    corollary, consequence, applications

    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
     Lemon
    -0.84
    junctive
    -0.79
     Widget
    -0.79
     req
    -0.77
    τικού
    -0.77
    ヱ
    -0.77
     COLLECTION
    -0.76
     Resort
    -0.75
     unicode
    -0.75
     SqlCommand
    -0.75
    POSITIVE LOGITS
     corollary
    2.38
     consequences
    2.23
    Corollary
    2.02
     consequence
    1.95
     Consequences
    1.75
     conséquence
    1.74
     applications
    1.73
    Consequences
    1.73
     Corollary
    1.70
    corollary
    1.56
    Activations Density 0.038%

    No Known Activations