© 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. 16304
    Prev
    Next
    INDEX
    Explanations

    years and quantities

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

    The neuron activates on numeric tokens, i.e. numbers and measured values expressed in digits.

    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
     adoro
    -0.83
     iy
    -0.78
     hạ
    -0.73
     Отечественной
    -0.73
    で作
    -0.72
    ounces
    -0.71
     mobile
    -0.71
    阶
    -0.70
     inches
    -0.70
    strength
    -0.69
    POSITIVE LOGITS
     mostrarán
    0.89
     theore
    0.88
     椒
    0.82
    क्षा
    0.80
    ocarcinoma
    0.79
     Años
    0.79
    }}^{(
    0.79
     theoretically
    0.78
    isNew
    0.78
     years
    0.77
    Activations Density 0.022%

    No Known Activations