© 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. 34-GEMMASCOPE-RES-131K
    7. 961
    Prev
    Next
    INDEX
    Explanations

    how things look or feel

    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
    looking
    -1.48
    Looking
    -1.41
     Looking
    -1.35
    looks
    -1.34
     looking
    -1.23
     LOOKING
    -1.20
     Looks
    -1.13
    look
    -1.08
     seeming
    -1.02
    Looks
    -1.01
    POSITIVE LOGITS
    身邊
    0.77
    ೖ
    0.77
     keduanya
    0.76
     sowohl
    0.75
     філь
    0.74
    不僅
    0.72
    Література
    0.72
     tasted
    0.71
    ierenden
    0.71
     both
    0.71
    Activations Density 0.029%

    No Known Activations