© 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. 49364
    Prev
    Next
    INDEX
    Explanations

    organization body association

    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
     가능
    -0.80
    comand
    -0.80
    tirer
    -0.79
     situasi
    -0.73
     可能
    -0.73
     project
    -0.73
     from
    -0.73
    CROSSTALK
    -0.73
     ermöglicht
    -0.72
    ᥙ
    -0.72
    POSITIVE LOGITS
     umbrella
    1.79
     organization
    1.68
     organisation
    1.42
     association
    1.34
     body
    1.32
     объеди
    1.28
    membership
    1.18
     membership
    1.18
     grouping
    1.14
    organizzazione
    1.13
    Activations Density 0.081%

    No Known Activations