© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73662
    Prev
    Next
    INDEX
    Explanations

    San Jose, California

    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
    鲼
    -2.27
    
    -1.74
    叽
    -1.63
    酹
    -1.60
    涠
    -1.59
     eagles
    -1.55
    але
    -1.52
     Hiking
    -1.49
    秾
    -1.48
     rojos
    -1.45
    POSITIVE LOGITS
    quê
    1.44
    蒾
    1.43
     his
    1.43
    <td>
    1.42
     returnValue
    1.42
     ―
    1.41
    ":
    1.34
    </th>
    1.34
     亜
    1.34
     showcased
    1.33
    Activations Density 0.015%

    No Known Activations