© 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. 64034
    Prev
    Next
    INDEX
    Explanations

    Tesla, Elon Musk, SpaceX

    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
     солдат
    -0.84
     зар
    -0.77
     Dresden
    -0.75
    ឥ
    -0.71
    য
    -0.71
    rower
    -0.70
    トラ
    -0.69
    🏓
    -0.68
     asc
    -0.68
    
    -0.66
    POSITIVE LOGITS
     Tesla
    1.56
    Tesla
    1.30
    Elon
    1.15
    tesla
    1.15
     Elon
    1.10
     tesla
    1.08
     Musk
    1.05
     HEPA
    0.98
     Model
    0.94
    Musk
    0.89
    Activations Density 0.005%

    No Known Activations