© 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. 22-GEMMASCOPE-RES-131K
    7. 34329
    Prev
    Next
    INDEX
    Explanations

    citations like [@ref]

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

    The neuron activates on tokens in mathematical probability problem statements (e.g. “prob of sequence … when …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.09
    Miejs
    -1.05
    حص
    -0.96
    Making
    -0.93
     preocu
    -0.91
     that
    -0.91
    Sant
    -0.90
    endaftar
    -0.90
    をお願い
    -0.90
    鎂
    -0.90
    POSITIVE LOGITS
    berly
    1.03
     idk
    0.91
    potamus
    0.91
    や
    0.91
    说出
    0.89
    isContained
    0.85
     gerekir
    0.85
    郃
    0.83
     janela
    0.83
     că
    0.82
    Activations Density 0.005%

    No Known Activations