© 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. 34-GEMMASCOPE-RES-131K
    7. 117232
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

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

    This neuron responds to numeric tokens or digit sequences (e.g. numbers, patent numbers, version 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_34/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
    prek
    -0.80
     PAIN
    -0.78
     popoli
    -0.76
     herum
    -0.72
    rih
    -0.71
     星座
    -0.71
    incere
    -0.70
     DAD
    -0.70
     Logged
    -0.69
     ANCI
    -0.69
    POSITIVE LOGITS
     ’
    2.36
     '
    1.44
    <'
    1.24
    tis
    1.23
     tis
    1.21
     \'
    1.20
     '_
    1.20
     "'
    1.13
    ='
    1.12
    /'
    1.11
    Activations Density 0.110%

    No Known Activations