© 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. 33394
    Prev
    Next
    INDEX
    Explanations

    superficial or tips

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

    The neuron fires on numeric tokens—i.e. digits or number sequences used in measurements or data values.

    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
    olarmente
    -0.81
    dania
    -0.81
     here
    -0.76
    logisch
    -0.74
     why
    -0.71
     always
    -0.71
     generally
    -0.71
     verho
    -0.71
    ատ
    -0.70
    季度
    -0.70
    POSITIVE LOGITS
     ±
    1.16
    ±
    1.14
     within
    0.88
    Within
    0.87
     (±
    0.86
     WITHIN
    0.84
     sideline
    0.82
    Bole
    0.81
    ͑
    0.80
    やはり
    0.79
    Activations Density 0.019%

    No Known Activations