© 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. 47728
    Prev
    Next
    INDEX
    Explanations

    experienced professionals

    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
     geniales
    -1.21
     podía
    -1.12
     dicen
    -1.09
    vedic
    -1.08
    demort
    -1.05
     específicamente
    -1.05
     specifically
    -1.05
     īpa
    -1.05
     menikmati
    -1.03
    遭
    -1.03
    POSITIVE LOGITS
     will
    1.37
     Akhir
    1.27
    only
    1.26
     Sén
    1.22
    known
    1.15
     Apabila
    1.09
     it
    1.09
    raient
    1.08
    ditionally
    1.07
     sierpnia
    1.06
    Activations Density 0.089%

    No Known Activations