© 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. 111695
    Prev
    Next
    INDEX
    Explanations

    sass, sassy, Pepsi

    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
     \
    -3.41
    1
    -2.80
    ):
    -2.56
    ));
    -2.47
    ).
    -2.34
     About
    -2.34
     complimented
    -2.27
    𓆟
    -2.27
    却又
    -2.27
    >
    -2.25
    POSITIVE LOGITS
     konus
    2.50
    𓋼
    2.39
    蔼
    2.31
     巷
    2.28
    锺
    2.23
    ೣ
    2.23
    籥
    2.17
     sinds
    2.13
     merawat
    2.06
     杯
    2.05
    Activations Density 0.010%

    No Known Activations