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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21986
    Prev
    Next
    INDEX
    Explanations

    street name 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
    </strong>
    -2.45
    焄
    -2.16
    vanju
    -2.09
    ”:
    -2.03
    
    -1.95
    呖
    -1.89
    ),”
    -1.88
    "]);
    -1.85
    趼
    -1.80
     — 
    -1.77
    POSITIVE LOGITS
     '
    2.64
    '
    2.44
    "
    2.34
    .,
    2.08
    \
    1.99
    *
    1.98
    /
    1.77
    
    1.70
     ('
    1.63
    儿童
    1.63
    Activations Density 0.013%

    No Known Activations