© 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. 4510
    Prev
    Next
    INDEX
    Explanations

    Welcome to

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

    The neuron detects documents that open with “Welcome to” followed immediately by a numeric identifier (a version, episode, or other number).

    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
     सामने
    0.76
    盾
    0.68
     والذي
    0.66
    ઓમાં
    0.66
    ).
    0.65
    )
    0.65
     sanction
    0.64
     निका
    0.64
     цього
    0.64
    ㈡
    0.63
    POSITIVE LOGITS
     wisata
    0.78
    k
    0.77
    ir
    0.74
     compras
    0.73
     viagem
    0.73
     TRAVEL
    0.73
    TRAVEL
    0.73
    libat
    0.73
     genießen
    0.72
     viaje
    0.71
    Activations Density 0.007%

    No Known Activations