© 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. 118371
    Prev
    Next
    INDEX
    Explanations

    creating or promoting positive outcomes

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

    The neuron activates on numeric tokens, spotting numbers (e.g. counts, years, measurements) 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
     BEAUT
    -1.45
    因为它
    -1.44
    vaila
    -1.42
    slightly
    -1.40
    nachron
    -1.38
     PREVENT
    -1.37
     οποία
    -1.27
    腘
    -1.27
    albeit
    -1.27
    但是在
    -1.27
    POSITIVE LOGITS
     a
    4.16
     an
    2.80
     better
    2.25
     greater
    2.09
     and
    1.98
     more
    1.85
     effective
    1.78
     stronger
    1.78
     strong
    1.60
     efficient
    1.56
    Activations Density 0.097%

    No Known Activations