© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    gotten my, gotten this, gotten 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
    e
    -3.11
    z
    -2.48
    ஂ
    -2.44
    ES
    -2.41
    b
    -2.34
    you
    -2.33
    just
    -2.31
    g
    -2.28
    🢒
    -2.28
    嶄
    -2.22
    POSITIVE LOGITS
    '
    3.25
    
    2.66
    .
    2.64
     sämtliche
    2.59
    .")
    2.48
    
    2.44
    "
    2.42
    }),
    2.42
     relativamente
    2.39
     vastly
    2.38
    Activations Density 0.001%

    No Known Activations