© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5350
    Prev
    Next
    INDEX
    Explanations

    social contexts or foreign languages

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

    The neuron activates on numeric tokens (digits, multi-digit numbers, and numeric sequences, including decimals and percentages).

    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_24_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
     thence
    0.89
    ;
    0.88
     precluded
    0.79
     variously
    0.77
     interposed
    0.74
     examined
    0.73
     whose
    0.73
     occurs
    0.73
     preserved
    0.72
     ;
    0.71
    POSITIVE LOGITS
     fintech
    1.16
     Fiverr
    1.11
     shitty
    1.10
     españa
    1.06
    Airbnb
    1.06
     bisschen
    1.04
     hoodies
    1.04
     esports
    1.02
     millennials
    1.02
     интернете
    1.02
    Activations Density 0.951%

    No Known Activations