© 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. 72887
    Prev
    Next
    INDEX
    Explanations

    numbers and Roman numerals

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

    The neuron is picking out numeric tokens that include a decimal point.

    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
     euró
    -0.95
    Nhưng
    -0.93
    ムラ
    -0.90
    ጸ
    -0.90
    避け
    -0.90
     ferait
    -0.90
     chcete
    -0.89
    發生
    -0.86
    НЫ
    -0.86
    ARON
    -0.85
    POSITIVE LOGITS
     natürlich
    0.93
    ığında
    0.93
     sebuah
    0.93
     presencia
    0.84
    ------
    0.84
    ],
    0.83
    ө
    0.82
     skup
    0.82
     and
    0.81
     },
    0.81
    Activations Density 0.051%

    No Known Activations