© 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. 40929
    Prev
    Next
    INDEX
    Explanations

    star ratings and emojis

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

    The neuron activates on decorative bullet‐style symbols (e.g. “★”, “○”) used as list or emphasis markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    浥
    -2.67
     RSITY
    -2.58
    ဴ
    -2.56
     manifests
    -2.52
    stateMutability
    -2.42
     adequate
    -2.38
     thinks
    -2.38
    ᭝
    -2.33
     enhances
    -2.33
     encourages
    -2.33
    POSITIVE LOGITS
    to
    2.77
    archiwizowane
    2.67
     várias
    2.66
    Of
    2.64
     tp
    2.58
    羕
    2.53
    がっ
    2.52
    ta
    2.48
    ꔹ
    2.47
     reiter
    2.44
    Activations Density 0.000%

    No Known Activations