© 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. 65564
    Prev
    Next
    INDEX
    Explanations

    shooter

    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
    ῞
    -2.66
     \"
    -2.44
    。
    -2.30
    \
    -2.28
     alot
    -2.23
    w
    -2.23
     continúas
    -2.22
    /'
    -2.22
     abuelos
    -2.20
    ]
    -2.20
    POSITIVE LOGITS
    </i>
    3.05
    ри
    2.56
    </h1>
    2.56
    骓
    2.52
     They
    2.47
    </h3>
    2.47
    </sub>
    2.34
    𓋼
    2.33
    iqué
    2.28
     heading
    2.27
    Activations Density 0.003%

    No Known Activations