© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99681
    Prev
    Next
    INDEX
    Explanations

    1963 or 1964

    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
    </strong>
    -1.84
    一点点
    -1.58
    さっそく
    -1.58
    </sup>
    -1.57
    に入って
    -1.56
     nacidos
    -1.53
     действует
    -1.51
    一个月
    -1.50
    こども
    -1.50
    旃
    -1.48
    POSITIVE LOGITS
    ↵↵
    2.17
    1
    2.02
    '
    1.61
    hemiah
    1.55
            
    1.55
    .
    1.52
    не
    1.50
    بق
    1.48
    一番
    1.41
    lampu
    1.39
    Activations Density 0.033%

    No Known Activations