© 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. 90775
    Prev
    Next
    INDEX
    Explanations

    actor and editor guilds

    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
    ksom
    -0.91
    hending
    -0.87
     excite
    -0.81
     છ
    -0.78
     braz
    -0.75
    сіб
    -0.72
    lní
    -0.72
    ír
    -0.71
     اداری
    -0.70
     adoles
    -0.69
    POSITIVE LOGITS
     union
    2.08
     SAG
    1.64
    union
    1.57
     guild
    1.55
     Guild
    1.45
    guild
    1.41
    SAG
    1.34
    Guild
    1.30
    UNION
    1.19
    Union
    1.15
    Activations Density 0.016%

    No Known Activations