© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130980
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens (sequences of digits), i.e. it detects numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    headers and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     same
    -1.17
    nextProps
    -1.13
    MAXN
    -1.09
    erba
    -1.09
    づけ
    -1.02
     getType
    -1.02
     from
    -1.02
     wichtigste
    -1.01
    をしました
    -1.01
    TURE
    -1.01
    POSITIVE LOGITS
     reager
    1.20
    wać
    1.12
     avoient
    1.09
    ٲ
    1.09
     pierdas
    1.07
    しかも
    1.04
     strå
    1.02
    sihkan
    1.00
    の
    0.99
     fumée
    0.98
    Activations Density 0.004%

    No Known Activations