© 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. 44914
    Prev
    Next
    INDEX
    Explanations

    phrases starting with say

    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
    潆
    -2.19
    
    -2.14
     умова
    -2.14
     stycznia
    -2.09
    arraycopy
    -2.08
    鈇
    -2.03
     These
    -2.02
     Each
    -1.98
     этом
    -1.94
    atação
    -1.94
    POSITIVE LOGITS
    ti
    2.33
    er
    2.27
    “
    2.09
     possib
    2.03
    </i>
    1.98
    said
    1.97
    ol
    1.91
    
    1.88
     recentemente
    1.88
     magnific
    1.87
    Activations Density 0.115%

    No Known Activations