© 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. 2230
    Prev
    Next
    INDEX
    Explanations

    He fought in wars

    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
    målet
    -0.83
     मुझे
    -0.79
    걷
    -0.76
     Jalan
    -0.74
    èvent
    -0.74
    ół
    -0.73
     Leningrad
    -0.73
    Nee
    -0.73
     Morin
    -0.72
    weekday
    -0.72
    POSITIVE LOGITS
     fighting
    3.47
     fought
    3.28
     fight
    3.16
    fighting
    2.92
    Fighting
    2.55
    fight
    2.53
     serving
    2.52
     fights
    2.47
    Fight
    2.42
     Fighting
    2.38
    Activations Density 0.098%

    No Known Activations