© 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. 34-GEMMASCOPE-RES-131K
    7. 80788
    Prev
    Next
    INDEX
    Explanations

    TTC riders

    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_34/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
     Whilst
    -2.25
     whilst
    -2.20
    Whilst
    -2.09
     our
    -1.31
     Amongst
    -1.30
     skall
    -1.27
     (~
    -1.23
    にて
    -1.23
     نمود
    -1.22
     bahkan
    -1.20
    POSITIVE LOGITS
     —
    1.56
     

    1.31
     didn
    1.25
     doesn
    1.24
     wouldn
    1.22
     makkelijk
    1.18
    ेमाल
    1.16
     
    1.16
     Unesco
    1.16
     --
    1.15
    Activations Density 0.038%

    No Known Activations