© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69872
    Prev
    Next
    INDEX
    Explanations

    game mechanics and abilities

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

    The neuron detects references to core game entities or resources (e.g. resources, units, weapons, abilities, cards) in strategy‐style game descriptions.

    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
     today
    -1.23
    enumii
    -1.06
     estamos
    -1.03
    .*;
    
    -1.03
    fiehlt
    -1.02
    gebnis
    -1.02
     because
    -1.02
    ଂ
    -1.02
     yesterday
    -1.01
    šanu
    -1.00
    POSITIVE LOGITS
     you
    1.44
     your
    1.25
     each
    1.18
    Each
    1.15
    each
    1.13
     Each
    1.13
    gradable
    1.09
     reminiscent
    1.07
    Votre
    1.04
     unlock
    1.03
    Activations Density 0.038%

    No Known Activations