© 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. 73361
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers or punctuation

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

    The neuron activates on standalone numeric tokens (e.g. years, counts, and other numbers).

    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
    czerw
    -1.23
     about
    -1.15
    諴
    -0.98
     }],
    -0.98
     in
    -0.96
    Já
    -0.91
    Nossa
    -0.91
    zessin
    -0.90
    Dobrý
    -0.89
    ometries
    -0.88
    POSITIVE LOGITS
     torner
    1.06
    nt
    1.06
     estremamente
    1.05
    了下去
    1.02
    来ました
    1.02
    簷
    1.01
     specialmente
    1.01
     essenziale
    0.99
     ovvero
    0.98
    tafogo
    0.96
    Activations Density 0.005%

    No Known Activations