© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    contact information

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

    The neuron selectively activates on numeric sequences (especially multi‐digit tokens like phone‐number fragments or other 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
    3
    0.51
    1
    0.50
    :
    0.50
    4
    0.49
    R
    0.46
    5
    0.44
    ::
    0.43
    iidae
    0.43
    Types
    0.43
    <sup>
    0.42
    POSITIVE LOGITS
     teléfono
    0.55
     PHONE
    0.54
     jugador
    0.54
     النموذج
    0.52
    ഷ്യ
    0.52
     delantero
    0.51
     salesperson
    0.51
    陕西
    0.51
    بوون
    0.51
    atán
    0.50
    Activations Density 0.030%

    No Known Activations