© 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. 35167
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases

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

    The neuron is primarily detecting individual digit tokens (numerals) 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
    موس
    -1.27
    𓄹
    -1.25
     mikina
    -1.22
     vernis
    -1.20
     setiap
    -1.20
     zapato
    -1.20
     noires
    -1.17
     joli
    -1.16
    Nazwa
    -1.15
     atau
    -1.14
    POSITIVE LOGITS
    P
    1.39
    F
    1.38
    T
    1.32
    N
    1.31
    O
    1.26
    C
    1.22
    J
    1.22
    Y
    1.21
    ar
    1.20
    l
    1.18
    Activations Density 0.002%

    No Known Activations