© 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. 83055
    Prev
    Next
    INDEX
    Explanations

    density and percentage measurements

    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
     vaya
    -0.75
    BackColor
    -0.70
    กลาง
    -0.65
    蜊
    -0.65
    優しい
    -0.64
     視
    -0.64
    jspb
    -0.63
     Toner
    -0.63
     RUS
    -0.63
     פס
    -0.63
    POSITIVE LOGITS
     density
    1.43
     SG
    1.32
     gravity
    1.32
     Density
    1.30
     Gravity
    1.29
    density
    1.23
     densité
    1.20
    gravity
    1.18
    Density
    1.16
    Gravity
    1.14
    Activations Density 0.011%

    No Known Activations