© 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. 76686
    Prev
    Next
    INDEX
    Explanations

    ups and downs

    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
    〆
    -0.80
     inoltre
    -0.79
    或是
    -0.77
     añadió
    -0.77
    荘
    -0.76
    ündigt
    -0.75
     posing
    -0.74
    āti
    -0.73
     hinted
    -0.73
     hinting
    -0.73
    POSITIVE LOGITS
     ups
    1.95
    Ups
    1.79
     Ups
    1.77
     highs
    1.71
     twists
    1.69
     vicissitudes
    1.52
     downs
    1.45
    downs
    1.32
     fortunes
    1.30
    ups
    1.24
    Activations Density 0.034%

    No Known Activations