© 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. 42540
    Prev
    Next
    INDEX
    Explanations

    social media and networks

    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
     last
    -1.70
     that
    -1.65
     unless
    -1.51
     return
    -1.50
    六十
    -1.49
     rest
    -1.42
    ruguay
    -1.42
    白衣
    -1.41
     Moreover
    -1.40
     Problemen
    -1.39
    POSITIVE LOGITS
    嗵
    1.77
    柃
    1.58
    茕
    1.55
     $^{\
    1.52
    踽
    1.48
    茘
    1.48
    !»
    1.41
    ...»
    1.39
     issus
    1.38
     först
    1.36
    Activations Density 0.022%

    No Known Activations