© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102120
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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
     When
    -2.70
     специалисты
    -2.48
    というわけで
    -2.48
     Two
    -2.42
     Surprisingly
    -2.39
    \
    -2.31
     been
    -2.31
     scrutin
    -2.30
     Following
    -2.16
     Its
    -2.14
    POSITIVE LOGITS
    }=\
    3.02
    𓋼
    2.58
    .”
    2.28
    }+\
    2.28
    an
    2.27
     ſen
    2.27
    mycompany
    2.23
     Anſ
    2.19
    
    2.17
    to
    2.16
    Activations Density 0.004%

    No Known Activations