© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79202
    Prev
    Next
    INDEX
    Explanations

    power up

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

    The neuron strongly fires on gameplay action verbs and commands (e.g. “fire,” “equip,” “attack,” “pause”).

    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
    Battlefield
    -0.81
    complished
    -0.77
     Nelson
    -0.75
    WithString
    -0.75
    Tone
    -0.75
     ст
    -0.75
    田市
    -0.75
    freien
    -0.75
    spania
    -0.75
    Alive
    -0.74
    POSITIVE LOGITS
     upgrade
    1.51
     upgraded
    1.46
     upgrades
    1.34
     upgrading
    1.23
     charge
    1.10
     Upgrade
    1.08
     Upgrades
    1.02
     upgra
    0.99
     basic
    0.97
     stronger
    0.97
    Activations Density 0.010%

    No Known Activations