© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14008
    Prev
    Next
    INDEX
    Explanations

    scores X to Y

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

    The neuron activates on numeric tokens (multi‐digit numbers and game‐score figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    chaise
    -1.05
    امین
    -1.03
     such
    -1.00
    outube
    -0.99
    otoro
    -0.94
    estero
    -0.90
    Supplementary
    -0.89
    kauft
    -0.88
    masti
    -0.86
    न्ह
    -0.85
    POSITIVE LOGITS
     corolla
    1.02
    氾
    0.88
    Mí
    0.88
    周泽
    0.88
     konsep
    0.87
    liet
    0.87
    spra
    0.86
    alucía
    0.83
    تحميل
    0.83
    EDEFAULT
    0.83
    Activations Density 0.004%

    No Known Activations