© 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. 60932
    Prev
    Next
    INDEX
    Explanations

    code comments and snippets

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

    The neuron is picking out standalone numeric tokens (i.e. words consisting of digits).

    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
     maxi
    -0.80
     ranchers
    -0.71
     Maximal
    -0.71
     bled
    -0.71
    setMax
    -0.70
     Maxi
    -0.69
     MAX
    -0.69
     Vier
    -0.69
    max
    -0.66
     autobio
    -0.66
    POSITIVE LOGITS
     weapon
    0.66
    FEC
    0.65
     Strengths
    0.65
     بک
    0.65
     إن
    0.65
    pokem
    0.64
    isDisplayed
    0.64
    smt
    0.63
    kok
    0.63
    Strengths
    0.63
    Activations Density 0.058%

    No Known Activations