© 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. 45014
    Prev
    Next
    INDEX
    Explanations

    file loading or initialization

    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
     considérons
    -1.61
    kwür
    -1.27
     {
    -1.26
     utilise
    -1.23
     endeavours
    -1.22
     любы
    -1.19
    {~
    -1.18
    会出现
    -1.16
     valeur
    -1.16
     —
    -1.16
    POSITIVE LOGITS
     zarówno
    1.64
     поэтому
    1.48
     Absicht
    1.46
     and
    1.38
    Also
    1.34
    Ƞ
    1.33
     גם
    1.33
     ursprüng
    1.32
     dessutom
    1.32
     wobec
    1.30
    Activations Density 0.009%

    No Known Activations