© 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. 112894
    Prev
    Next
    INDEX
    Explanations

    Pope Benedict XVI, Benedictine, feud, antitrust

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

    The neuron is sharply tuned to detect the word “adversity.”

    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
    d
    -3.41
    ia
    -2.75
    O
    -2.69
    In
    -2.64
    er
    -2.55
    M
    -2.47
    y
    -2.31
    el
    -2.28
     conveniences
    -2.27
     Mostly
    -2.22
    POSITIVE LOGITS
     kompatibel
    2.44
     และ
    2.41
    岽
    2.39
    錞
    2.31
     alça
    2.25
    ﺢ
    2.23
    橚
    2.19
    aure
    2.19
    卺
    2.16
    ޞ
    2.13
    Activations Density 0.004%

    No Known Activations