© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64403
    Prev
    Next
    INDEX
    Explanations

    digital game platforms and distribution

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

    The neuron strongly responds to list-style, metadata-heavy passages describing digital game sales (e.g. dates, prices, platforms, and sale terms).

    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
    TokenNameRBRACE
    -0.94
     Instagram
    -0.93
    Subviews
    -0.90
    Groot
    -0.89
     الس
    -0.84
     Vila
    -0.82
    uangan
    -0.82
     NFC
    -0.82
     TikTok
    -0.82
    CGRectMake
    -0.82
    POSITIVE LOGITS
     Steam
    3.55
    Steam
    3.38
     steam
    2.88
    steam
    2.61
     STEAM
    2.11
     GOG
    1.70
     Humble
    1.56
     Valve
    1.50
    Valve
    1.46
     launcher
    1.45
    Activations Density 0.076%

    No Known Activations