© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107127
    Prev
    Next
    INDEX
    Explanations

    new leader or boss

    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
    どうしても
    -0.91
    他に
    -0.88
     requerida
    -0.87
    oplasma
    -0.84
    itare
    -0.84
    octobre
    -0.84
    িয়ে
    -0.84
    的部分
    -0.82
    ôl
    -0.82
    ຼ
    -0.82
    POSITIVE LOGITS
     head
    3.53
     director
    2.23
     heads
    2.19
     leader
    2.02
     chief
    1.96
     chairman
    1.93
    head
    1.91
     jefe
    1.68
     chair
    1.63
     boss
    1.62
    Activations Density 0.082%

    No Known Activations