© 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. 107073
    Prev
    Next
    INDEX
    Explanations

    video game features and qualities

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects numeric review ratings and their associated score headings (e.g. the digits and category labels in a game review score breakdown).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    パフォーマンス
    -0.94
    nejšie
    -0.92
    Discography
    -0.91
     useful
    -0.88
    useful
    -0.85
    ليج
    -0.85
     intervenciones
    -0.84
     የ
    -0.84
    neurs
    -0.83
     coveted
    -0.83
    POSITIVE LOGITS
     addictive
    1.79
     gameplay
    1.68
     addic
    1.59
     polished
    1.39
     playable
    1.33
    polished
    1.32
     polish
    1.28
     polishing
    1.19
     fun
    1.17
     graphics
    1.17
    Activations Density 0.059%

    No Known Activations