© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84792
    Prev
    Next
    INDEX
    Explanations

    icon classes (font awesome, glyphicons, ionicons)

    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
    也有
    -1.80
    Also
    -1.73
     também
    -1.71
     również
    -1.62
     también
    -1.57
     with
    -1.55
     także
    -1.53
     and
    -1.51
    También
    -1.42
     גם
    -1.42
    POSITIVE LOGITS
    嘹
    1.42
    都好
    1.38
     saludables
    1.36
     suas
    1.33
    各自
    1.27
    спонд
    1.27
    ियम
    1.26
    ppuden
    1.26
    bertas
    1.26
     vemos
    1.24
    Activations Density 0.007%

    No Known Activations