© 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. 385
    Prev
    Next
    INDEX
    Explanations

    expanding businesses and services

    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
    יפור
    -0.81
    ₾
    -0.81
    zonder
    -0.81
    Debate
    -0.80
    opti
    -0.78
    gör
    -0.77
    になってしまう
    -0.77
    REPLACE
    -0.77
    ྲ
    -0.77
    🛩
    -0.77
    POSITIVE LOGITS
     branching
    3.64
     expand
    3.55
     branch
    3.55
     branched
    3.44
    branch
    3.25
     expanded
    3.16
     expanding
    3.16
    expand
    3.00
    Branch
    2.95
     expands
    2.91
    Activations Density 0.128%

    No Known Activations