© 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. 99541
    Prev
    Next
    INDEX
    Explanations

    CSRF tokens

    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
    -1.66
    玬
    -1.62
     orgánica
    -1.58
    </td>
    -1.55
     -:
    -1.52
     vixion
    -1.52
    1
    -1.50
     destinada
    -1.50
     elétrica
    -1.48
     مناط
    -1.45
    POSITIVE LOGITS
     zamanda
    1.60
     These
    1.60
     increíble
    1.57
     untuk
    1.53
    ="
    1.50
     altas
    1.48
    lgari
    1.46
    ⪯
    1.43
     bellas
    1.42
    各样的
    1.42
    Activations Density 0.006%

    No Known Activations