© 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. 38810
    Prev
    Next
    INDEX
    Explanations

    As

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

    The neuron activates on numeric tokens (digits or numbers, including integers and decimals).

    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
    ҵ
    -1.00
     может
    -0.99
    дження
    -0.98
     colorear
    -0.98
    BROOK
    -0.94
    Ғ
    -0.92
     tästä
    -0.92
     możesz
    -0.91
     também
    -0.91
     теперь
    -0.91
    POSITIVE LOGITS
     to
    1.14
     L
    0.94
     S
    0.82
     Se
    0.81
    L
    0.79
     l
    0.79
     a
    0.78
     end
    0.74
     are
    0.73
     is
    0.72
    Activations Density 0.002%

    No Known Activations