© 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. 22390
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ?
    -2.05
    鏖
    -1.88
     tromper
    -1.81
    戆
    -1.80
     billede
    -1.77
    ACEAE
    -1.72
    鲮
    -1.71
    彼女は
    -1.70
    梘
    -1.69
    雰
    -1.67
    POSITIVE LOGITS
     
    2.05
    ––
    1.88
                
    1.86
     of
    1.78
    ↵
    1.76
       
    1.72
    on
    1.72
    vv
    1.68
    ፨
    1.66
                    
    1.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.