© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45454
    Prev
    Next
    INDEX
    Explanations

    Plano, Banco, Diablo, Blanco, Leia

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

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

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ?
    -3.09
    都是在
    -2.69
    /
    -2.55
    '
    -2.55
    *
    -2.48
    ’’
    -2.44
    就像是
    -2.41
     Btn
    -2.39
    都是
    -2.30
    甚至是
    -2.25
    POSITIVE LOGITS
    ?”
    3.05
     '
    2.92
    ዖ
    2.75
    逦
    2.72
    壟
    2.70
    !”
    2.66
    两人的
    2.47
    ⡦
    2.45
    蠵
    2.44
    𓆜
    2.42
    Activations Density 0.005%

    No Known Activations