© 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. 10-GEMMASCOPE-RES-131K
    4. 12398
    Prev
    Next
    INDEX
    Explanations

    quantities after "more than"

    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_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
    1
    -2.91
     it
    -2.30
     are
    -2.23
     This
    -2.19
     esperan
    -2.17
    9
    -2.11
    4
    -2.11
     facilitar
    -2.09
     I
    -2.08
    6
    -2.08
    POSITIVE LOGITS
    ,’
    2.81
    剮
    2.44
    indrome
    2.41
    ༴
    2.41
     dozen
    2.30
     chré
    2.20
    welijk
    2.20
     convincingly
    2.17
    書いた
    2.17
    ing
    2.17
    Activations Density 0.020%

    No Known Activations