© 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. 91431
    Prev
    Next
    INDEX
    Explanations

    location, beta, styles

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

    The neuron responds strongly to numeric constants (integer literals) in the code.

    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
     against
    -0.85
    ppes
    -0.75
    Depuis
    -0.73
    της
    -0.73
    ..<
    -0.72
     歯科
    -0.71
     campuran
    -0.70
    tové
    -0.69
    sds
    -0.68
    wyżs
    -0.68
    POSITIVE LOGITS
     StyleSheet
    1.10
     theme
    1.02
    Theme
    0.90
    镜像
    0.77
     Theme
    0.77
     Grandma
    0.75
     тему
    0.74
     themes
    0.74
    ranslated
    0.72
    AJ
    0.72
    Activations Density 0.025%

    No Known Activations