© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8602
    Prev
    Next
    INDEX
    Explanations

    battery depletion

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

    The neuron fires on numeric tokens with decimal points, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caves
    0.55
     Year
    0.55
     Sovere
    0.52
    लिसिस
    0.52
     ಭೂ
    0.52
    桦
    0.52
     Peer
    0.51
    nus
    0.51
     হাকি
    0.50
    迠
    0.50
    POSITIVE LOGITS
     deple
    2.05
     depleted
    2.03
     deplete
    2.03
     depletion
    2.02
     replenish
    1.96
     replen
    1.87
     replenished
    1.84
     replenishment
    1.66
     refill
    1.41
     agot
    1.41
    Activations Density 0.513%

    No Known Activations