© 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. 78798
    Prev
    Next
    INDEX
    Explanations

    company management employees HR

    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
     vitale
    -1.14
    цыі
    -1.11
     alté
    -1.10
     ALREADY
    -1.05
     bronzo
    -1.02
    剎
    -1.02
     etti
    -1.02
     beſt
    -1.00
     augmente
    -1.00
     حت
    -0.99
    POSITIVE LOGITS
     company
    1.52
     management
    1.40
     employees
    1.33
     there
    1.26
     employee
    1.23
     managers
    1.23
     Company
    1.22
     they
    1.18
     HR
    1.17
     Management
    1.16
    Activations Density 0.015%

    No Known Activations