© 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. 93185
    Prev
    Next
    INDEX
    Explanations

    rel or Rel attribute

    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
     Goss
    -0.90
    Maha
    -0.85
    siswa
    -0.84
    ributos
    -0.84
     exquisite
    -0.82
     brilliant
    -0.81
     Offizielle
    -0.81
    ɫ
    -0.80
    另一個
    -0.79
     сколько
    -0.77
    POSITIVE LOGITS
     Rel
    1.66
     REL
    1.54
    REL
    1.45
     rel
    1.33
    Rel
    1.30
     Relay
    1.08
     rela
    1.05
    rel
    0.99
    RELL
    0.98
    its
    0.97
    Activations Density 0.076%

    No Known Activations