© 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. 32713
    Prev
    Next
    INDEX
    Explanations

    organizations and affiliations

    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
     occidentalis
    -0.75
    Sites
    -0.73
    locs
    -0.70
    apis
    -0.70
    館
    -0.68
    馆
    -0.68
     bibit
    -0.68
    皱
    -0.68
    iosis
    -0.68
    /:
    -0.68
    POSITIVE LOGITS
     religious
    1.36
     clubs
    1.34
     political
    1.31
     terrorist
    1.20
     sports
    1.07
     professional
    1.03
     associations
    1.02
    Affinity
    1.02
     voluntary
    1.02
     club
    1.01
    Activations Density 0.114%

    No Known Activations