© 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. 34-GEMMASCOPE-RES-131K
    4. 90751
    Prev
    Next
    INDEX
    Explanations

    citation markers

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

    The neuron is sensitive to multi-digit numeric sequences (long runs of digits, e.g. page or figure numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     or
    -1.57
     so
    -1.47
     What
    -1.38
     M
    -1.37
     what
    -1.32
     there
    -1.32
     There
    -1.32
     Many
    -1.31
     many
    -1.30
     Some
    -1.27
    POSITIVE LOGITS
     faciliter
    1.38
     moteurs
    1.34
    ஏ
    1.30
    킁
    1.28
     kapture
    1.28
    Spolja
    1.27
     véhicules
    1.27
     poils
    1.27
    ⇩
    1.26
    
    1.26
    Activations Density 0.004%

    No Known Activations