© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74132
    Prev
    Next
    INDEX
    Explanations

    all, everyone, everything

    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_10/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
     سایر
    -2.31
     também
    -1.91
    -1.89
    these
    -1.88
    他の
    -1.84
            
    -1.81
     столь
    -1.81
     cette
    -1.79
     denne
    -1.78
     gleichen
    -1.78
    POSITIVE LOGITS
     Everything
    2.45
    各样的
    2.28
     Everyone
    2.11
     There
    2.06
    始まり
    2.05
    鐧
    1.98
    ometry
    1.98
     所有
    1.85
     lebte
    1.84
    ometric
    1.81
    Activations Density 0.008%

    No Known Activations