© 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. 9802
    Prev
    Next
    INDEX
    Explanations

    Himalayan regions and names

    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
    硨
    -1.57
    ⛵
    -1.55
    ternut
    -1.48
    धारण
    -1.45
    ☕
    -1.44
    玏
    -1.44
    🏩
    -1.42
     comprimidos
    -1.41
    除此
    -1.41
    ⭐⭐
    -1.41
    POSITIVE LOGITS
     who
    2.05
     see
    1.53
    8
    1.50
    </em>
    1.40
    ’
    1.39
    </h2>
    1.38
    <strong>
    1.37
    苦
    1.35
    9
    1.34
    }$.
    1.29
    Activations Density 0.005%

    No Known Activations