© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63936
    Prev
    Next
    INDEX
    Explanations

    musical studies and theory

    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
     adapter
    -0.81
    ExceptionHandler
    -0.79
     garantit
    -0.77
     Danza
    -0.76
    MenuList
    -0.76
     calavera
    -0.75
     adaptor
    -0.74
     Jonson
    -0.74
    ηγ
    -0.74
    curl
    -0.74
    POSITIVE LOGITS
     theory
    1.77
     Theory
    1.64
    theory
    1.47
    Theory
    1.41
     teoria
    1.36
     theoretical
    1.35
     theories
    1.34
     THEORY
    1.31
     history
    1.30
     sight
    1.30
    Activations Density 0.024%

    No Known Activations