© 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. 34379
    Prev
    Next
    INDEX
    Explanations

    // delimiter

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

    This neuron activates on numeric tokens—i.e. number literals 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_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
    riturismo
    -0.99
     aliments
    -0.98
     hjel
    -0.96
     aldri
    -0.93
     kommit
    -0.93
     föres
    -0.92
    UNITIES
    -0.92
     endast
    -0.92
     ProtoMessage
    -0.91
     fortsatt
    -0.88
    POSITIVE LOGITS
    mathrm
    1.13
    _
    0.95
    ͜
    0.91
    desta
    0.88
     paramount
    0.85
     structure
    0.84
     both
    0.83
    }.
    0.82
     atm
    0.82
     mine
    0.81
    Activations Density 0.013%

    No Known Activations