© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113673
    Prev
    Next
    INDEX
    Explanations

    partial differential or class

    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
    </h3>
    -2.70
    gefügt
    -2.25
     This
    -2.17
     respectivas
    -2.17
     If
    -2.13
     You
    -2.03
    ))}
    -1.82
     invocation
    -1.82
    ++){
    
    -1.81
    grafa
    -1.79
    POSITIVE LOGITS
    ↵
    2.63
    2
    2.55
    oczes
    2.47
    3
    2.28
    -*
    2.23
    
    2.14
    ちなみに
    2.14
    -:
    2.11
    饃
    2.09
    *:
    2.03
    Activations Density 0.002%

    No Known Activations