© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11839
    Prev
    Next
    INDEX
    Explanations

    specific domain keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "tkinter" (a Python GUI library) or "Bahamas" (the country/location).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ſelf
    -3.09
    ❘
    -3.00
    apatalk
    -2.86
    愎
    -2.80
    
    -2.75
    岽
    -2.75
    
    -2.59
    🕗
    -2.58
    xvii
    -2.53
    蔼
    -2.53
    POSITIVE LOGITS
    e
    3.23
     
    3.13
    ?”
    3.03
    </em>
    3.02
    ”
    2.78
    0
    2.75
    1
    2.66
    i
    2.63
    jenigen
    2.63
    ti
    2.63
    Activations Density 0.010%

    No Known Activations