© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 639
    Prev
    Next
    INDEX
    Explanations

    Tennessee cities and courts

    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
    り物
    -1.41
     laughable
    -1.40
    炖
    -1.37
    ’
    -1.34
     tenacious
    -1.32
    мою
    -1.28
    TIPO
    -1.27
     $('#
    -1.26
    HARDWARE
    -1.24
    COMPUTER
    -1.23
    POSITIVE LOGITS
    </b>
    1.47
    le
    1.45
     vodi
    1.44
    ',
    
    1.43
    瑒
    1.39
    </i>
    1.35
     успе
    1.33
    ín
    1.32
    ds
    1.30
    dad
    1.27
    Activations Density 0.026%

    No Known Activations