© 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. 106267
    Prev
    Next
    INDEX
    Explanations

    DOIs and publication numbers

    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
    issy
    -1.02
     Preto
    -0.96
    satunya
    -0.93
    siert
    -0.91
     アクセ
    -0.89
    Phys
    -0.88
    仡
    -0.87
    ECTOS
    -0.87
     ldap
    -0.86
     Accesat
    -0.85
    POSITIVE LOGITS
    Rgds
    0.89
     Erweiter
    0.82
     Musk
    0.75
     なく
    0.71
    などで
    0.71
     İç
    0.70
     Muslim
    0.70
     этих
    0.69
     Wenger
    0.67
     Steuerung
    0.67
    Activations Density 0.005%

    No Known Activations