© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 482
    Prev
    Next
    INDEX
    Explanations

    word endings and beginnings

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

    The neuron is tuned to pick out tokens containing embedded digits (e.g. numbered annotations or alphanumeric sequences).

    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
    toDouble
    -1.48
    któ
    -1.36
    ₿
    -1.22
     we
    -1.18
    ⑦
    -1.14
    Ⅲ
    -1.13
    獃
    -1.13
    ☎️
    -1.13
    toFloat
    -1.13
     року
    -1.12
    POSITIVE LOGITS
     şun
    1.23
     العديد
    1.18
    aneity
    1.16
    oczes
    1.16
    Beschrijving
    1.14
    
    1.14
     değiştir
    1.13
    plication
    1.12
     -'
    1.12
    derry
    1.09
    Activations Density 0.125%

    No Known Activations