© 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. 5692
    Prev
    Next
    INDEX
    Explanations

    model names

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

    The neuron detects components of timestamp or log‐time markers (digits, colons, and enclosing brackets).

    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
     and
    0.62
     January
    0.57
     $\
    0.54
     or
    0.53
     <
    0.53
     andre
    0.53
     February
    0.52
     $
    0.52
     don
    0.52
     seven
    0.52
    POSITIVE LOGITS
    uerpo
    0.61
    তরাং
    0.55
    Arrival
    0.54
    Greeting
    0.54
    cityName
    0.54
    Agricult
    0.53
    ttore
    0.51
    btnLogout
    0.51
    etiti
    0.50
    Ofer
    0.50
    Activations Density 0.094%

    No Known Activations