© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9007
    Prev
    Next
    INDEX
    Explanations

    reduced

    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
    ING
    -2.34
     they
    -2.28
    銕
    -2.27
    
    -2.20
    킁
    -2.16
    筇
    -2.08
     restoran
    -2.05
    栳
    -2.02
     indiví
    -2.00
    秾
    -2.00
    POSITIVE LOGITS
    '
    2.38
    chtenstein
    2.30
     decreased
    2.23
    ness
    2.23
    levance
    2.22
    獃
    2.17
    年初
    2.11
    摭
    2.06
     mencionar
    2.05
    ).
    2.00
    Activations Density 0.008%

    No Known Activations