© 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. 34-GEMMASCOPE-RES-131K
    7. 31763
    Prev
    Next
    INDEX
    Explanations

    was founded or established

    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
    fries
    -0.81
    gnet
    -0.77
    kimi
    -0.75
    ід
    -0.75
     розви
    -0.73
    Processed
    -0.73
     скриншот
    -0.72
     generó
    -0.72
    ilera
    -0.71
     partecipazione
    -0.71
    POSITIVE LOGITS
     founded
    5.81
     Founded
    4.59
    Founded
    4.56
    founded
    4.25
     established
    3.83
     founding
    3.48
     formed
    3.42
    Established
    3.41
    成立
    3.41
     Established
    3.22
    Activations Density 0.315%

    No Known Activations