© 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. 92840
    Prev
    Next
    INDEX
    Explanations

    game mechanics and rules

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

    The neuron flags mentions of quantitative game‐mechanics terms—numbers and stats like HP, turns, damage, status effects, percentages, etc.—in gameplay discussions.

    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
     löytyy
    -1.20
    ASKA
    -1.15
    Therapy
    -1.15
    Föld
    -1.11
    ürlich
    -1.11
    LÄ
    -1.10
    Dobrý
    -1.09
    疖
    -1.09
     ー
    -1.09
     facilement
    -1.08
    POSITIVE LOGITS
     from
    1.53
     regardless
    1.45
     you
    1.41
     if
    1.30
     displayed
    1.17
     or
    1.15
     while
    1.15
    结算
    1.13
     still
    1.09
     only
    1.07
    Activations Density 0.047%

    No Known Activations