© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83259
    Prev
    Next
    INDEX
    Explanations

    first and last name pairs

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

    The neuron fires specifically on the bare underscore token ( “_” ), flagging uses of “_” in identifiers (e.g. internal helper names).

    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
     meticulously
    -0.88
    ümmer
    -0.86
    çak
    -0.85
     mostly
    -0.84
     negras
    -0.83
     דער
    -0.82
    信息
    -0.82
    ospital
    -0.82
    Интер
    -0.81
     dirilis
    -0.81
    POSITIVE LOGITS
    ician
    0.84
     añadió
    0.82
    ient
    0.82
    izacion
    0.82
    carus
    0.80
    enda
    0.79
    quisites
    0.79
    iste
    0.79
     putty
    0.79
    amide
    0.78
    Activations Density 0.000%

    No Known Activations