© 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. 2493
    Prev
    Next
    INDEX
    Explanations

    "$(BUILD_DIR)" variable usage

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

    The neuron strongly activates on tokens that are numeric or contain digits.

    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
     conocidas
    -0.96
    Obviously
    -0.92
     aunque
    -0.90
    だけでなく
    -0.90
     fo
    -0.88
     pierwsze
    -0.85
    Personally
    -0.84
    obviously
    -0.84
    too
    -0.83
     pierwszy
    -0.83
    POSITIVE LOGITS
    wachsenen
    0.96
    Hp
    0.94
     valentin
    0.93
     thofe
    0.91
    王的
    0.90
     melissa
    0.90
     profuse
    0.89
    </h2>
    0.89
    Törté
    0.88
     Guangdong
    0.88
    Activations Density 0.049%

    No Known Activations