© 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. 22-GEMMASCOPE-RES-131K
    7. 128096
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on standalone numeric tokens (integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    chr or aa identifiers

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

    table or database rows that contain numeric IDs or indices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kabát
    -1.48
     pelu
    -1.42
     TÉ
    -1.40
     anún
    -1.38
    ̨
    -1.37
     vagyok
    -1.36
     Tratado
    -1.35
     bilder
    -1.34
     elefante
    -1.34
     beszél
    -1.34
    POSITIVE LOGITS
     only
    1.36
     not
    1.28
    6
    1.23
     
    1.22
     everything
    1.22
    全都
    1.22
    3
    1.20
    8
    1.20
    4
    1.17
    9
    1.14
    Activations Density 0.015%

    No Known Activations