© 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. 103442
    Prev
    Next
    INDEX
    Explanations

    state of being

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     stopping
    -0.74
     occurrence
    -0.74
    occurrence
    -0.71
    uploads
    -0.68
     होने
    -0.67
     existence
    -0.67
     adalah
    -0.67
    =>{
    -0.66
     Likelihood
    -0.65
     why
    -0.65
    POSITIVE LOGITS
     está
    3.73
     están
    2.95
    Está
    2.84
     estão
    2.83
     estaba
    2.80
     estar
    2.80
     Está
    2.64
     estava
    2.52
    está
    2.38
     està
    2.30
    Activations Density 0.015%

    No Known Activations