© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30424
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and ideas

    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
    bited
    -1.77
     ouver
    -1.66
    romeda
    -1.66
    dienne
    -1.55
    wheres
    -1.53
     wille
    -1.52
     obvio
    -1.52
    (')
    -1.52
     -->
    
    -1.50
     pior
    -1.49
    POSITIVE LOGITS
     and
    4.28
     which
    3.02
     or
    2.84
     to
    2.52
     but
    2.45
     since
    2.27
     so
    2.25
     for
    2.05
     like
    2.02
     of
    1.99
    Activations Density 0.195%

    No Known Activations