© 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. 103797
    Prev
    Next
    INDEX
    Explanations

    questions about current actions

    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
    妩
    -1.38
    ERICAL
    -1.05
     borbo
    -1.02
     péro
    -1.02
     ifølge
    -1.02
    लब्
    -1.00
    obrá
    -1.00
    äus
    -1.00
     беже
    -1.00
    $.}
    -0.98
    POSITIVE LOGITS
     вен
    1.19
    TokenNameDOT
    1.05
    Microsoft
    1.04
     развер
    0.99
     bastion
    0.98
     Microsoft
    0.98
     resiliency
    0.97
     topology
    0.96
    \
    0.95
    Topology
    0.95
    Activations Density 0.588%

    No Known Activations