© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    Cola/Kola/Bola/Mora + word part

    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
     Mini
    -0.87
    ATK
    -0.87
    IEU
    -0.81
    logne
    -0.78
     Grover
    -0.75
     MINI
    -0.75
     Mayer
    -0.75
    hnout
    -0.73
    érature
    -0.73
    trá
    -0.73
    POSITIVE LOGITS
     aufgenommen
    0.79
    itarian
    0.73
    IsTrue
    0.71
     零
    0.68
    igue
    0.68
     APT
    0.68
    それから
    0.68
    LOADER
    0.67
     comprehen
    0.67
     moratorium
    0.67
    Activations Density 0.033%

    No Known Activations