© 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. 10-GEMMASCOPE-RES-131K
    7. 70345
    Prev
    Next
    INDEX
    Explanations

    money, year, or agriculture related

    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
     it
    -1.13
    sacrific
    -1.04
     its
    -1.02
    ction
    -1.02
    blouse
    -1.00
    arrings
    -0.99
     central
    -0.98
    incorpor
    -0.98
    bohemian
    -0.96
    increased
    -0.95
    POSITIVE LOGITS
     arbeitet
    1.30
     bidra
    1.28
    ées
    1.25
     afferma
    1.24
    ")
    1.23
    。”
    1.20
     already
    1.20
    vatten
    1.19
     estimés
    1.17
    */
    1.16
    Activations Density 0.021%

    No Known Activations