© 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. 10-GEMMASCOPE-RES-131K
    7. 113735
    Prev
    Next
    INDEX
    Explanations

    Hyatt, Chalmers, Daphne

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

    The neuron detects tokens containing the letter sequence “app.”

    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
    "
    -3.19
    s
    -3.02
    ࿙
    -2.66
    って
    -2.56
    )
    -2.52
     If
    -2.48
    is
    -2.42
    自己的
    -2.39
     To
    -2.38
    this
    -2.33
    POSITIVE LOGITS
    最后由
    2.83
    涐
    2.73
    蠵
    2.53
    骉
    2.50
    鋌
    2.42
    
    2.41
    齪
    2.38
     navide
    2.31
    ”)
    2.28
     발생
    2.23
    Activations Density 0.004%

    No Known Activations