© 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. 58383
    Prev
    Next
    INDEX
    Explanations

    questions and technical issues

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

    The neuron fires on long runs of blank‐space tokens (multi‐space indentations or separators).

    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
     (
    -2.05
     even
    -1.86
     most
    -1.41
     this
    -1.39
     new
    -1.38
     F
    -1.38
    .
    -1.38
     L
    -1.36
     many
    -1.36
    1
    -1.34
    POSITIVE LOGITS
    courir
    1.65
    
    1.63
     únicos
    1.62
    pasti
    1.60
    mte
    1.60
    ...."
    1.58
    écnicas
    1.55
    noční
    1.52
     sooo
    1.51
     praticamente
    1.51
    Activations Density 0.192%

    No Known Activations