© 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. 30441
    Prev
    Next
    INDEX
    Explanations

    win over opponent

    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
    allin
    -0.83
     relate
    -0.83
     attraverso
    -0.83
    går
    -0.83
     nét
    -0.81
    ñó
    -0.81
     Overlay
    -0.80
    quard
    -0.80
     Saison
    -0.79
    ctin
    -0.79
    POSITIVE LOGITS
     over
    2.91
     над
    1.30
    over
    1.20
     against
    1.16
     über
    1.12
     över
    1.07
    nable
    0.98
    campista
    0.85
    against
    0.85
    atory
    0.84
    Activations Density 0.024%

    No Known Activations