© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103904
    Prev
    Next
    INDEX
    Explanations

    collaboration and unity

    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
    gió
    -0.84
    kursi
    -0.84
    }}-\
    -0.81
    sendRedirect
    -0.79
    ioutil
    -0.79
     };
    -0.78
    visit
    -0.77
     via
    -0.77
    thy
    -0.77
    Integr
    -0.76
    POSITIVE LOGITS
     working
    2.52
     united
    2.27
     together
    2.17
     banding
    2.06
     объеди
    2.06
     come
    2.03
     banded
    1.99
    working
    1.99
     collaborate
    1.95
     coming
    1.92
    Activations Density 0.099%

    No Known Activations