© 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. 44527
    Prev
    Next
    INDEX
    Explanations

    superlative endings

    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
    ezy
    -1.90
    ureusement
    -1.73
     Они
    -1.73
     aprove
    -1.73
     pretože
    -1.72
    openConnection
    -1.72
    牖
    -1.72
     duże
    -1.70
    芎
    -1.68
     прида
    -1.65
    POSITIVE LOGITS
    most
    2.52
    ↵
    2.41
    end
    1.97
    best
    1.93
    та
    1.91
     perpé
    1.89
    几乎
    1.88
    幾個
    1.82
    或许
    1.82
    ፳
    1.81
    Activations Density 0.004%

    No Known Activations