© 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. 111202
    Prev
    Next
    INDEX
    Explanations

    Tweeting, TSP, Cly, Egan, NAB

    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
    s
    -3.38
    菒
    -2.64
    .
    -2.58
    ᠂
    -2.58
     estadounid
    -2.58
    놋
    -2.53
    냑
    -2.53
    We
    -2.52
    that
    -2.48
    看起来
    -2.48
    POSITIVE LOGITS
    至於
    2.41
     så
    2.22
    多次
    2.14
    
    2.11
    
    2.06
     sorta
    2.06
     così
    2.06
    jaqueta
    2.05
    については
    2.05
     suas
    2.05
    Activations Density 0.023%

    No Known Activations