© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation following titles

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

    The neuron detects numeric tokens (numbers, especially multi‐digit numerals such as years or counts).

    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
     so
    -1.34
     helps
    -1.30
     will
    -1.29
     now
    -1.27
     easy
    -1.27
     or
    -1.23
     this
    -1.16
     on
    -1.16
     by
    -1.16
     it
    -1.13
    POSITIVE LOGITS
     boissons
    1.20
     momentous
    1.15
     INCREASE
    1.12
    웡
    1.09
    味わい
    1.09
     équilibre
    1.09
    lighed
    1.09
     больших
    1.08
     ſol
    1.07
    少しずつ
    1.07
    Activations Density 0.004%

    No Known Activations