© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86316
    Prev
    Next
    INDEX
    Explanations

    BMW cars

    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
    大部分
    -2.45
    This
    -2.31
    ꯸
    -2.27
     стоковая
    -2.23
    枓
    -2.19
     Особенно
    -2.16
     they
    -2.13
    当然
    -2.08
    <bos>
    -2.08
     Только
    -2.06
    POSITIVE LOGITS
    蔸
    2.78
    ”،
    2.53
    哙
    2.50
     Februar
    2.48
    >$
    2.47
    玙
    2.47
     Januar
    2.45
    苤
    2.39
                
    2.36
     '-
    2.31
    Activations Density 0.003%

    No Known Activations