© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    location followed by description

    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
    ↵
    -1.59
    Jeep
    -1.35
     these
    -1.30
     especially
    -1.27
     particularly
    -1.27
    頃から
    -1.25
     DATOS
    -1.23
    ⅰ
    -1.20
    )։
    -1.20
    тами
    -1.19
    POSITIVE LOGITS
     into
    1.41
    ,
    1.41
     to
    1.35
     में
    1.34
    一楼
    1.27
     maravilh
    1.25
    營業時間
    1.25
    atação
    1.25
    好在
    1.24
    Then
    1.23
    Activations Density 0.016%

    No Known Activations