© 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. 10-GEMMASCOPE-RES-131K
    7. 71403
    Prev
    Next
    INDEX
    Explanations

    scanned document image links

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

    The neuron is detecting numeric tokens that include decimal points (i.e. floating-point numbers).

    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
     ию
    -2.02
     renowned
    -1.97
     continually
    -1.93
    ふん
    -1.89
     сент
    -1.88
     ihre
    -1.86
     conspicuously
    -1.84
    A
    -1.83
     suitably
    -1.79
     we
    -1.77
    POSITIVE LOGITS
    🌟
    1.97
    as
    1.90
    phans
    1.88
    natured
    1.88
    thodox
    1.84
    }));
    1.80
    ！”
    1.77
    🌼
    1.73
     teilweise
    1.71
     Undang
    1.71
    Activations Density 0.004%

    No Known Activations