© 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. 59315
    Prev
    Next
    INDEX
    Explanations

    potential issues and their causes

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

    This neuron activates on unusually long individual tokens (i.e. longer words).

    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
     importants
    -0.95
     smak
    -0.90
     pittores
    -0.89
     planches
    -0.89
     unie
    -0.89
        
    -0.88
     existant
    -0.88
     FORMA
    -0.88
    IIT
    -0.88
    Technologies
    -0.88
    POSITIVE LOGITS
     something
    1.95
     either
    1.63
     Either
    1.48
     culprit
    1.48
     faulty
    1.48
     Something
    1.45
     somehow
    1.44
     либо
    1.36
    something
    1.33
     caused
    1.28
    Activations Density 0.122%

    No Known Activations