© 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. 21157
    Prev
    Next
    INDEX
    Explanations

    "not only" $+$ verb phrases

    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
     in
    -2.30
    {
    -2.02
    ⃚
    -1.95
    ↵↵
    -1.84
     
    -1.73
     more
    -1.73
     less
    -1.73
    蠖
    -1.70
     by
    -1.70
     eğer
    -1.59
    POSITIVE LOGITS
     вами
    2.11
    vieron
    2.08
     mauva
    2.06
    睃
    2.02
    ⎆
    1.98
    
    1.95
    AGRAM
    1.89
    鲧
    1.87
     he
    1.84
    ligator
    1.84
    Activations Density 0.008%

    No Known Activations