© 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. 113138
    Prev
    Next
    INDEX
    Explanations

    possessives like 's

    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
     Completely
    -2.47
    What
    -2.39
    Surprisingly
    -2.36
    ”
    -2.33
     Following
    -2.33
     Surprisingly
    -2.27
     After
    -2.19
     achieving
    -2.14
     Extremely
    -2.13
    Using
    -2.08
    POSITIVE LOGITS
    
    2.94
    archiwizowane
    2.80
     renowned
    2.59
    憷
    2.44
    佝
    2.39
     денег
    2.39
    ቕ
    2.36
    䜣
    2.36
    
    2.34
     WIL
    2.33
    Activations Density 0.046%

    No Known Activations