© 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. 22-GEMMASCOPE-RES-131K
    7. 104443
    Prev
    Next
    INDEX
    Explanations

    overlap and intersection

    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_22/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
    S
    -2.77
     to
    -2.59
    C
    -2.30
     If
    -2.25
    齶
    -2.23
    琑
    -2.23
    しております
    -2.00
     نيوز
    -2.00
    H
    -2.00
     podemos
    -1.97
    POSITIVE LOGITS
    퐸
    2.75
     of
    2.63
    寕
    2.59
    
    2.55
    METHODOLOGY
    2.50
    𐐀
    2.47
    鈇
    2.47
    ated
    2.47
    芣
    2.44
    咵
    2.42
    Activations Density 0.007%

    No Known Activations