© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35522
    Prev
    Next
    INDEX
    Explanations

    new or again

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

    The main thing this neuron does is detect numeric tokens (numbers, including integers and decimals).

    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
     final
    -0.86
    tualmente
    -0.84
     finale
    -0.82
     FINAL
    -0.81
     Finale
    -0.78
    उत्तर
    -0.76
    Final
    -0.76
     الجز
    -0.76
    ълга
    -0.75
    Invent
    -0.72
    POSITIVE LOGITS
     new
    1.62
     again
    1.45
    Again
    1.25
    again
    1.24
     anew
    1.20
     afresh
    1.20
     fresh
    1.20
    重新
    1.16
     Again
    1.15
    ใหม่
    1.12
    Activations Density 0.036%

    No Known Activations