© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56844
    Prev
    Next
    INDEX
    Explanations

    We + action verb

    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
    Negative Logits
     all
    -1.05
     pertemuan
    -1.05
    atzung
    -1.04
     ratusan
    -1.01
     keputusan
    -0.99
    ၌
    -0.99
     kisah
    -0.98
     révélé
    -0.98
     from
    -0.96
    bantu
    -0.96
    POSITIVE LOGITS
     performed
    1.94
     conducted
    1.55
     use
    1.43
    performed
    1.34
     used
    1.30
     also
    1.29
     chose
    1.28
     applied
    1.26
     elected
    1.23
     compared
    1.20
    Activations Density 0.177%

    No Known Activations