© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97995
    Prev
    Next
    INDEX
    Explanations

    it or

    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
     voire
    -1.12
     DOR
    -0.91
     pö
    -0.90
    ovací
    -0.90
     eventuell
    -0.90
    EDR
    -0.89
     exemplu
    -0.88
    
    -0.88
    ætte
    -0.88
    ckets
    -0.84
    POSITIVE LOGITS
     or
    3.06
    かどうか
    1.28
     and
    1.24
     yes
    1.17
     not
    1.07
    or
    1.07
     Or
    1.05
     aside
    0.94
    Or
    0.86
     didn
    0.86
    Activations Density 0.035%

    No Known Activations