© 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. 106643
    Prev
    Next
    INDEX
    Explanations

    comma followed by conjunction

    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
     lâmpada
    -1.18
     finalement
    -1.16
     exemplaires
    -1.11
     caneta
    -1.11
     roupa
    -1.09
    Bjs
    -1.09
     ceket
    -1.08
    櫚
    -1.07
     Voyages
    -1.06
     tatuagem
    -1.05
    POSITIVE LOGITS
     or
    2.45
     including
    2.42
     and
    2.42
     whether
    2.11
     as
    1.97
     if
    1.89
     to
    1.86
     unless
    1.83
     except
    1.80
     such
    1.60
    Activations Density 0.108%

    No Known Activations