© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    reading lines

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

    This neuron activates on function or method calls that read input (e.g. various forms of “readLine”/“readline”).

    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
    s
    -3.73
    d
    -2.98
    e
    -2.89
     However
    -2.69
     Other
    -2.64
    на
    -2.61
     {
    -2.56
    on
    -2.55
    ):
    -2.52
    h
    -2.50
    POSITIVE LOGITS
    
    3.08
     ausein
    2.91
     夜景
    2.80
    茕
    2.77
    wiſe
    2.70
     vaisseaux
    2.69
     fahrrad
    2.67
    眛
    2.64
    涐
    2.61
    阏
    2.58
    Activations Density 0.001%

    No Known Activations