© 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. 65428
    Prev
    Next
    INDEX
    Explanations

    risk management

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

    This neuron responds to the indentation and punctuation tokens (braces, quotes, commas, colons, and the runs of whitespace) used in structured (e.g. JSON‐style) markup.

    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
    Advertisements
    -0.93
     Camping
    -0.83
    cibly
    -0.77
    カチ
    -0.76
    Rapport
    -0.74
     dj
    -0.73
     atmos
    -0.71
     soutě
    -0.71
    accu
    -0.71
    might
    -0.71
    POSITIVE LOGITS
     likelihood
    1.95
     probability
    1.75
     risk
    1.70
     Likelihood
    1.59
    likelihood
    1.48
     severity
    1.40
     Risk
    1.37
    Likelihood
    1.28
    risk
    1.28
     probabilities
    1.27
    Activations Density 0.012%

    No Known Activations