© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26281
    Prev
    Next
    INDEX
    Explanations

    other languages

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

    The neuron activates on numerical tokens—digits and decimal numbers—marking occurrences of quantitative figures within the text.

    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
     очеред
    -1.02
    ％
    -0.97
    visiae
    -0.93
    ，”
    -0.91
     solicitud
    -0.90
    meros
    -0.89
    deauna
    -0.85
     tarta
    -0.82
    apeake
    -0.82
     obligé
    -0.82
    POSITIVE LOGITS
     other
    2.39
     अन्य
    1.73
    Other
    1.51
     diğer
    1.47
    其他
    1.47
     інших
    1.46
     остальных
    1.39
     Other
    1.38
     других
    1.37
     innych
    1.32
    Activations Density 0.200%

    No Known Activations