© 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. 22-GEMMASCOPE-RES-131K
    7. 12671
    Prev
    Next
    INDEX
    Explanations

    the followed by entities

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

    The neuron activates on numeric tokens (i.e. sequences 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_22/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
     kupa
    -1.73
    などを
    -1.70
     Itali
    -1.70
     komfor
    -1.66
     kamera
    -1.62
     seks
    -1.59
     hemd
    -1.59
     flink
    -1.54
     kultur
    -1.53
     infrastruktur
    -1.53
    POSITIVE LOGITS
     During
    1.91
     Even
    1.84
     While
    1.77
     When
    1.73
     With
    1.72
     Although
    1.68
     Before
    1.66
     as
    1.58
     If
    1.57
     Since
    1.55
    Activations Density 0.078%

    No Known Activations