© 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. 10-GEMMASCOPE-RES-131K
    7. 86158
    Prev
    Next
    INDEX
    Explanations

    choral music and choir activities

    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_10/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
     Surprisingly
    -2.05
     Perhaps
    -1.91
     After
    -1.82
    What
    -1.80
    Have
    -1.76
    禕
    -1.76
    lhes
    -1.75
    Our
    -1.73
     disesuaikan
    -1.72
     можно
    -1.71
    POSITIVE LOGITS
    _
    2.22
     raiſ
    1.91
    </b>
    1.71
     bijoux
    1.66
    tires
    1.66
     waw
    1.65
     RAJ
    1.63
    凩
    1.57
    壜
    1.57
     nage
    1.56
    Activations Density 0.008%

    No Known Activations