© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38588
    Prev
    Next
    INDEX
    Explanations

    contrast or transition words

    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_22/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
    隈
    -0.91
    Jog
    -0.88
     hul
    -0.85
    gänge
    -0.84
    質な
    -0.82
     اللاعب
    -0.82
     savior
    -0.81
    ⒐
    -0.80
     rigide
    -0.79
     کہ
    -0.79
    POSITIVE LOGITS
     our
    1.42
     this
    1.25
     project
    1.13
     other
    0.99
     subsequent
    0.95
     deeper
    0.95
     iniciado
    0.92
     more
    0.91
     perdida
    0.90
     initiative
    0.90
    Activations Density 0.020%

    No Known Activations