© 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. 11928
    Prev
    Next
    INDEX
    Explanations

    certain [X]

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

    The neuron activates on numeric tokens that include a decimal point—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_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
    ু
    0.96
    न
    0.89
    ieth
    0.89
    児
    0.89
    नियां
    0.86
    َ
    0.84
    aktu
    0.82
    i
    0.81
    खोरी
    0.81
     Nearest
    0.80
    POSITIVE LOGITS
    はこの
    1.15
     ciertas
    1.08
     ciertos
    1.06
    其他
    1.05
     деятельность
    1.05
     bestimmte
    1.01
     aspects
    0.98
    段階
    0.97
    மற்ற
    0.97
     பகுதிகளில்
    0.96
    Activations Density 0.062%

    No Known Activations