© 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. 127644
    Prev
    Next
    INDEX
    Explanations

    around, near, range, order

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

    The neuron activates on numeric tokens containing a decimal point (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
    gól
    -1.46
     each
    -1.34
     integrados
    -1.34
     eléctricos
    -1.28
     enfrentan
    -1.26
     two
    -1.25
     Entdecken
    -1.24
    3
    -1.24
    1
    -1.22
     dager
    -1.21
    POSITIVE LOGITS
    潆
    1.38
    硨
    1.33
    鹛
    1.32
     incluso
    1.30
    ⅘
    1.30
     appropriated
    1.29
    ją
    1.27
    ಲ್
    1.26
    ENOMEM
    1.26
    鋦
    1.25
    Activations Density 0.052%

    No Known Activations