© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84325
    Prev
    Next
    INDEX
    Explanations

    upstanding patriots

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

    The neuron responds strongly to unusually long tokens, regardless of their specific meaning.

    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
     but
    -1.77
     the
    -1.55
    <eos>
    -1.36
    嶽
    -1.36
     because
    -1.32
     then
    -1.30
     sentidos
    -1.28
     are
    -1.28
     and
    -1.27
     now
    -1.26
    POSITIVE LOGITS
     geene
    1.71
     aspira
    1.63
     maksi
    1.60
     kuj
    1.59
     milj
    1.58
     adverten
    1.53
     teras
    1.52
     teka
    1.51
     bestia
    1.49
     pulsa
    1.49
    Activations Density 0.201%

    No Known Activations