© 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. 92633
    Prev
    Next
    INDEX
    Explanations

    game attributes, levels, and rarity

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

    The neuron strongly activates on numeric tokens and quantitative details (e.g. digits, percentages, numeric parameters).

    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
    tisches
    -0.84
     termé
    -0.84
    дика
    -0.81
    assero
    -0.78
    IBinder
    -0.78
    Corey
    -0.78
    负担
    -0.77
     報
    -0.77
    Bailey
    -0.76
     báo
    -0.76
    POSITIVE LOGITS
     rarity
    2.47
    Rarity
    1.80
     attribute
    1.76
     attributes
    1.59
    rarity
    1.38
     tier
    1.38
    属性
    1.35
     type
    1.30
     Attribute
    1.24
    屬
    1.24
    Activations Density 0.014%

    No Known Activations