© 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. 92663
    Prev
    Next
    INDEX
    Explanations

    cricket and tennis games

    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
     durata
    -0.71
    ighbor
    -0.71
    蘚
    -0.71
    청
    -0.70
     entrevist
    -0.70
     okna
    -0.69
    phazard
    -0.69
     /**
    -0.69
     Munk
    -0.69
     parseFrom
    -0.69
    POSITIVE LOGITS
     overs
    1.57
    Over
    1.10
     ओवर
    1.08
     over
    1.05
     Over
    1.04
     Overs
    0.99
     maiden
    0.99
     OVER
    0.89
    OVER
    0.88
    overs
    0.88
    Activations Density 0.024%

    No Known Activations