© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117685
    Prev
    Next
    INDEX
    Explanations

    Moreover, furthermore, followed by comma

    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
     البته
    -1.12
     sezonu
    -1.04
     donc
    -1.02
    niosek
    -1.02
     azonban
    -1.02
     однако
    -0.98
    ？）
    -0.98
     in
    -0.98
     for
    -0.95
     però
    -0.94
    POSITIVE LOGITS
    $
    1.19
     schild
    1.18
     femininos
    1.16
     groen
    1.15
     it
    1.13
     acrescent
    1.13
     composés
    1.13
     pronounced
    1.13
     certaines
    1.11
    踯
    1.09
    Activations Density 0.031%

    No Known Activations