© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83816
    Prev
    Next
    INDEX
    Explanations

    topic followed by related word

    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
     "[
    -1.22
     “[
    -1.11
     reportedly
    -1.01
    "[
    -1.00
    “[
    -0.98
    喃
    -0.80
     необходимые
    -0.80
    ꜥ
    -0.79
     '[
    -0.79
    According
    -0.78
    POSITIVE LOGITS
    decimals
    0.90
     promet
    0.85
    cipais
    0.84
    oramic
    0.80
     anew
    0.80
    Cus
    0.77
     vibra
    0.77
     sirop
    0.76
     رخ
    0.75
     Barrera
    0.75
    Activations Density 0.100%

    No Known Activations