© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80704
    Prev
    Next
    INDEX
    Explanations

    so as to

    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
     wykonane
    -2.28
     帽
    -2.27
     embarc
    -2.23
     vacunas
    -2.20
    읭
    -2.13
     maceta
    -2.11
    ﺅ
    -2.11
     cérami
    -2.11
    itize
    -2.09
     llantas
    -2.09
    POSITIVE LOGITS
     to
    7.91
     of
    3.02
     You
    2.66
     It
    2.53
     This
    2.14
     And
    2.06
     Thank
    2.06
     
    2.03
     but
    2.02
    s
    1.92
    Activations Density 0.839%

    No Known Activations