© 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. 67968
    Prev
    Next
    INDEX
    Explanations

    ss / rss / oss endings

    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
    д
    -2.75
     That
    -2.63
     While
    -2.58
    But
    -2.55
     stemming
    -2.48
    残酷
    -2.47
    спомина
    -2.44
    る
    -2.44
     achieves
    -2.42
     blatantly
    -2.41
    POSITIVE LOGITS
    ⢌
    2.78
    และ
    2.75
     we
    2.70
    
    2.58
     BEING
    2.53
    縢
    2.48
    ⮜
    2.47
    and
    2.45
     exceptionally
    2.44
     impec
    2.42
    Activations Density 0.040%

    No Known Activations