© 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. 58168
    Prev
    Next
    INDEX
    Explanations

    alleged ritual or called

    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
    Midwest
    -0.93
     corrupción
    -0.84
    FEATURES
    -0.81
    Derived
    -0.81
    になれば
    -0.79
    adro
    -0.77
    Joke
    -0.77
    乎
    -0.77
     sanctified
    -0.76
     Africans
    -0.75
    POSITIVE LOGITS
    ızlık
    0.90
     suspected
    0.85
     pants
    0.81
     publie
    0.81
     führte
    0.79
     brut
    0.79
     suspects
    0.79
    erted
    0.79
     rituals
    0.77
    elementAt
    0.77
    Activations Density 0.016%

    No Known Activations