© 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. 30817
    Prev
    Next
    INDEX
    Explanations

    function composition and definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to single‐letter variable names and “Let”/definition phrases used in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Når
    -0.74
    onik
    -0.69
    лим
    -0.68
     Ikke
    -0.65
    ַּ
    -0.65
     mitosis
    -0.65
    жин
    -0.63
    龥
    -0.63
     Camb
    -0.63
     Willy
    -0.63
    POSITIVE LOGITS
     composition
    3.50
     compose
    3.22
     compositions
    3.16
     Composition
    3.09
    compose
    3.03
    Composition
    2.94
     composed
    2.88
     компози
    2.86
    Compose
    2.81
    composition
    2.80
    Activations Density 0.050%

    No Known Activations