© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127890
    Prev
    Next
    INDEX
    Explanations

    xml in code and documents

    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
     They
    -3.28
    ↵
    -3.20
     soothe
    -2.55
    riturismo
    -2.44
    );
    -2.36
    などが
    -2.31
    
    -2.23
     внешний
    -2.22
    ’
    -2.22
     ).
    -2.20
    POSITIVE LOGITS
    ޞ
    2.66
    衕
    2.61
    俢
    2.55
    𓆜
    2.55
     卵
    2.53
     restoran
    2.53
     こう
    2.53
    ቾ
    2.53
    鱚
    2.53
     sonriente
    2.52
    Activations Density 0.022%

    No Known Activations