© 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. 57538
    Prev
    Next
    INDEX
    Explanations

    Georgia and following specifics

    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
     unſ
    -3.22
    </strong>
    -3.05
    垕
    -2.77
    耵
    -2.73
    皛
    -2.70
    鈇
    -2.66
    
    -2.63
    諼
    -2.61
     所以
    -2.59
    
    -2.59
    POSITIVE LOGITS
    9
    2.67
    The
    2.58
    >
    2.41
    —
    2.41
    In
    2.41
    </td>
    2.41
     \
    2.36
    ，
    2.36
    踌
    2.34
    2
    2.30
    Activations Density 0.005%

    No Known Activations