© 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. 90748
    Prev
    Next
    INDEX
    Explanations

    biblical quotes and references

    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
    ceo
    -1.70
    often
    -1.44
     somewhat
    -1.44
    
    -1.38
    sometimes
    -1.36
    ękuję
    -1.34
    ౭
    -1.30
    ICIA
    -1.26
    possibly
    -1.23
     варианты
    -1.20
    POSITIVE LOGITS
     or
    1.73
    </i>
    1.31
     uvas
    1.27
    </b>
    1.23
    هة
    1.13
     exuberant
    1.13
    Divers
    1.09
     with
    1.09
    Warna
    1.09
     how
    1.08
    Activations Density 0.026%

    No Known Activations