© 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. 19233
    Prev
    Next
    INDEX
    Explanations

    items listed after including

    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
     jika
    -2.13
     atau
    -2.13
     ''
    -2.09
     yarar
    -2.09
    EDEFAULT
    -2.09
     '
    -2.08
     h
    -2.06
     Zü
    -2.03
    ENODE
    -1.99
    ("")]
    -1.97
    POSITIVE LOGITS
    
    2.53
     the
    2.52
    狌
    2.47
    ,..
    2.45
    玙
    2.38
    鸲
    2.38
    橚
    2.31
    :”
    2.31
    玧
    2.30
    𞤢
    2.25
    Activations Density 0.035%

    No Known Activations