© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    osteoporosis, Connie, Jar

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

    This neuron identifies numeric data values (especially floating‐point numbers) in 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_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
    瓩
    -3.55
    ſelves
    -2.92
     pantaloni
    -2.89
    ركز
    -2.86
    minaire
    -2.78
    你
    -2.70
     protagonisti
    -2.66
    我們
    -2.63
    剮
    -2.59
    ه
    -2.56
    POSITIVE LOGITS
     
    3.14
    ing
    2.94
    だけではなく
    2.64
     dando
    2.53
     The
    2.50
    凄い
    2.45
    に入れる
    2.44
    亖
    2.42
     deline
    2.42
     of
    2.39
    Activations Density 0.010%

    No Known Activations