© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    inside or outside

    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
     the
    -3.72
     to
    -2.34
    鹀
    -2.25
    </b>
    -2.13
    -2.11
     their
    -2.09
    ྜ
    -2.06
    >
    -1.95
    );

    -1.94
    1
    -1.88
    POSITIVE LOGITS
    恫
    2.28
     podido
    2.28
    聍
    2.27
    逞
    2.20
    tığı
    2.20
    脔
    2.17
     sabido
    2.17
     dejado
    2.08
    渦
    2.02
    拮
    1.98
    Activations Density 0.004%
    No Known Activations