© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31302
    Prev
    Next
    INDEX
    Explanations

    come to terms

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

    The neuron fires on verbs and noun combinations that express grappling with or coming to terms with something—e.g. “come to terms,” “come to grips,” or “wrestling with.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     نے
    -0.71
    piper
    -0.69
    ülen
    -0.69
     马
    -0.68
    ocardi
    -0.68
     citations
    -0.68
    zun
    -0.68
    arroll
    -0.68
    Filmography
    -0.67
     retval
    -0.67
    POSITIVE LOGITS
     come
    2.63
     coming
    2.36
     grips
    2.27
    Coming
    2.14
    Come
    2.09
     Coming
    2.06
    come
    2.05
    coming
    1.98
     comes
    1.95
     Come
    1.88
    Activations Density 0.029%

    No Known Activations