© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86534
    Prev
    Next
    INDEX
    Explanations

    'for' followed by common 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
    
    -2.55
    赑
    -2.52
    
    -2.42
    罍
    -2.36
    鱨
    -2.33
     regal
    -2.25
    槩
    -2.23
    皤
    -2.23
    柃
    -2.22
     فعالیت
    -2.20
    POSITIVE LOGITS
     ‘
    3.16
     (‘
    2.84
     Choosing
    2.81
    providedIn
    2.75
     Carefully
    2.73
     ‘‘
    2.69
     Previously
    2.63
     Whether
    2.59
    2
    2.56
    For
    2.53
    Activations Density 0.090%

    No Known Activations