© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90571
    Prev
    Next
    INDEX
    Explanations

    platinum and DLC

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

    The neuron strongly activates on numeric tokens or sequences—i.e. version numbers, codes, percentages, and other digit-heavy strings.

    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
     Think
    -0.90
    Think
    -0.88
     think
    -0.88
    Mari
    -0.83
     Mari
    -0.79
     info
    -0.75
     экран
    -0.75
    nmgp
    -0.75
     $$
    -0.73
     animaux
    -0.73
    POSITIVE LOGITS
     platinum
    0.96
    Platinum
    0.95
    platinum
    0.92
     nego
    0.86
     Rast
    0.85
     Platinum
    0.84
    DLC
    0.83
    ))/(
    0.81
     DLC
    0.80
     Rasp
    0.80
    Activations Density 0.008%

    No Known Activations