© 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. 22-GEMMASCOPE-RES-131K
    7. 27913
    Prev
    Next
    INDEX
    Explanations

    leadership and management

    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_22/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
     velkommen
    -1.08
    وحة
    -1.04
    륨
    -1.03
     fredag
    -1.03
     entire
    -1.01
     artikke
    -0.97
     overras
    -0.94
    mulher
    -0.94
    adag
    -0.93
     nửa
    -0.93
    POSITIVE LOGITS
     who
    1.14
     elite
    1.13
     leadership
    1.02
    controle
    0.89
    Leadership
    0.85
     whom
    0.84
     ambao
    0.84
    qualität
    0.82
     Privile
    0.82
     sente
    0.82
    Activations Density 0.097%

    No Known Activations