© 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. 10-GEMMASCOPE-RES-131K
    7. 103972
    Prev
    Next
    INDEX
    Explanations

    same, different, better, more

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

    The neuron activates on numeric tokens (e.g. integers or decimals), picking out numbers and numeric 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_10/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
    owany
    -1.45
    悫
    -1.42
    쨩
    -1.38
    ⬈
    -1.37
     dépenses
    -1.36
     ifølge
    -1.26
    ivotopis
    -1.26
     såsom
    -1.26
    着一个
    -1.26
    raient
    -1.24
    POSITIVE LOGITS
     different
    1.69
     that
    1.67
     both
    1.30
     actions
    1.28
     until
    1.28
     difficult
    1.28
     what
    1.27
     people
    1.27
     two
    1.25
     any
    1.18
    Activations Density 0.101%

    No Known Activations