© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68883
    Prev
    Next
    INDEX
    Explanations

    outcomes and results

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

    The neuron fires on numeric score and statistic tokens—i.e. it’s looking for numbers (often sports‐related scores or stats) 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
    蕺
    -1.66
     abbildung
    -1.53
    橚
    -1.52
     développer
    -1.51
    ౭
    -1.51
    湏
    -1.49
     marquer
    -1.47
     décider
    -1.47
     pourront
    -1.45
    敺
    -1.44
    POSITIVE LOGITS
     by
    2.00
     from
    1.59
     in
    1.47
     on
    1.43
     not
    1.38
     said
    1.31
     themselves
    1.27
    ฯ
    1.27
     via
    1.25
    .(
    1.22
    Activations Density 0.022%

    No Known Activations