© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    technical code and documentation

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

    The neuron flags capitalized tokens—words or identifiers beginning with an uppercase letter.

    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
    mikro
    -0.79
    ற்ப
    -0.75
    cratic
    -0.75
     puffer
    -0.73
    COX
    -0.71
    贩
    -0.71
     dust
    -0.70
    erm
    -0.68
     fennel
    -0.68
     ok
    -0.68
    POSITIVE LOGITS
    izz
    0.67
     cartes
    0.66
    цы
    0.66
    реди
    0.63
     ал
    0.62
     Barclay
    0.61
    izu
    0.61
     середи
    0.60
    Deg
    0.60
     Debug
    0.60
    Activations Density 0.046%

    No Known Activations