© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4194
    Prev
    Next
    INDEX
    Explanations

    dealing with predictions

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

    The neuron fires on the very first meaningful word of a new text block or paragraph—that is, it detects segment beginnings.

    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
    ę
    0.82
     ditu
    0.81
    ServletException
    0.78
    abhavam
    0.78
    contains
    0.68
    니어
    0.68
    ક
    0.68
    piegel
    0.67
    ติดตาม
    0.67
    sebastian
    0.67
    POSITIVE LOGITS
     І
    0.99
    𝑳
    0.81
    𝒂
    0.80
     Р
    0.79
    筝
    0.79
     时
    0.79
     nghề
    0.78
     existencia
    0.77
     为
    0.76
    𝑨
    0.75
    Activations Density 0.000%

    No Known Activations