© 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. 107930
    Prev
    Next
    INDEX
    Explanations

    coach, led, headed

    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
     mengaku
    -0.87
     trzech
    -0.80
    给你
    -0.79
     опубли
    -0.75
    äsent
    -0.74
     verfügb
    -0.74
     dzisiaj
    -0.73
     lauded
    -0.73
     Hammer
    -0.72
     khoe
    -0.71
    POSITIVE LOGITS
     led
    3.17
     presided
    3.08
     coached
    2.64
     chaired
    2.58
     headed
    2.48
     supervised
    2.41
     overseen
    2.23
     commanded
    2.06
     directed
    1.98
     owned
    1.98
    Activations Density 0.418%

    No Known Activations