© 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. 34-GEMMASCOPE-RES-131K
    7. 54023
    Prev
    Next
    INDEX
    Explanations

    depending on the situation

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

    The neuron is primarily detecting numeric tokens (numbers or digit sequences) 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_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
    "-"
    -1.25
     idéia
    -1.17
     nyní
    -1.16
     nowa
    -1.15
     aluminio
    -1.14
    .'-
    -1.10
    😪
    -1.09
    直至
    -1.09
    😤
    -1.07
    🤟
    -1.06
    POSITIVE LOGITS
     you
    2.08
     your
    1.79
     while
    1.77
     if
    1.70
     that
    1.62
     While
    1.59
    While
    1.40
     depending
    1.36
    You
    1.35
     If
    1.31
    Activations Density 0.034%

    No Known Activations