© 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. 10-GEMMASCOPE-RES-131K
    7. 101260
    Prev
    Next
    INDEX
    Explanations

    numeric values containing 9

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

    The neuron strongly activates whenever it encounters the specific numeral “89.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鳢
    -2.75
    ，，
    -2.42
    咵
    -2.41
    焄
    -2.38
     to
    -2.38
    歃
    -2.34
    嶮
    -2.27
    ).
    -2.20
    氿
    -2.17
    ㉓
    -2.17
    POSITIVE LOGITS
    –
    2.41
     
    2.36
    Your
    2.00
    心を
    1.95
     температуре
    1.95
     imponer
    1.94
    —
    1.93
    The
    1.91
    ふたり
    1.89
     пти
    1.88
    Activations Density 0.017%

    No Known Activations