© 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. 43911
    Prev
    Next
    INDEX
    Explanations

    it seems to me

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

    This neuron primarily detects occurrences of the word “to.”

    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
     you
    -2.06
     it
    -1.68
     作り
    -1.66
    着他
    -1.55
    箇所
    -1.53
     cierra
    -1.52
     katk
    -1.51
     they
    -1.49
     there
    -1.48
    J
    -1.47
    POSITIVE LOGITS
    They
    1.74
    );
    1.66
    よって
    1.59
    –
    1.52
    .).
    1.52
    ра
    1.50
    儈
    1.49
    ."
    1.39
    rhosis
    1.35
    ни
    1.34
    Activations Density 0.017%

    No Known Activations