© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33796
    Prev
    Next
    INDEX
    Explanations

    political, ethnic, and sectarian divisions

    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
     oce
    -0.96
    Reducer
    -0.95
     luigi
    -0.92
    BEAT
    -0.91
     indipendente
    -0.90
     EXE
    -0.90
     tomat
    -0.88
     ducati
    -0.88
     vins
    -0.87
    ENZA
    -0.87
    POSITIVE LOGITS
     ethnic
    1.45
     elite
    1.27
     identity
    1.20
     ethnicity
    1.20
     spoilers
    1.14
     identities
    1.06
     Identity
    1.05
     eth
    1.05
     cle
    1.05
     cliente
    1.04
    Activations Density 0.018%

    No Known Activations