© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90696
    Prev
    Next
    INDEX
    Explanations

    invitations to participate

    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
    berra
    -0.91
     CHOOSE
    -0.86
     carreaux
    -0.85
     semblent
    -0.84
    Sl
    -0.84
    付き合い
    -0.83
     miljö
    -0.81
    })();
    
    -0.80
    Suffix
    -0.80
     fizeram
    -0.80
    POSITIVE LOGITS
     become
    1.71
     becoming
    1.71
     Become
    1.68
    Become
    1.61
     contribute
    1.61
    become
    1.55
     join
    1.50
     Becoming
    1.44
     learn
    1.36
    Becoming
    1.34
    Activations Density 0.044%

    No Known Activations