© 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. 71010
    Prev
    Next
    INDEX
    Explanations

    The FINE, Product, induction

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

    The neuron strongly activates on numeric tokens—especially standalone numbers and version‐style number sequences (e.g. “Version 4.0.0.3”).

    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
     their
    -1.62
     smaller
    -1.14
     series
    -1.09
    五百
    -1.05
    夫妻
    -1.05
    三十
    -1.03
    一道
    -1.03
     larger
    -1.03
     its
    -1.00
    ள்
    -1.00
    POSITIVE LOGITS
    küche
    1.31
    TERNS
    1.22
    Neko
    1.14
    strates
    1.13
     familières
    1.13
    Moda
    1.11
    💮
    1.11
    Inhalts
    1.11
    Brigitte
    1.10
    Niko
    1.08
    Activations Density 0.011%

    No Known Activations