© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9986
    Prev
    Next
    INDEX
    Explanations

    mean or 0

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

    The neuron steadily ramps up activation over the course of a passage and fires most strongly on tokens appearing near the end of a text.

    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
    in
    0.88
    wür
    0.85
     PAOK
    0.83
    𝐖
    0.83
     möchten
    0.82
     กล่าว
    0.82
     verwenden
    0.82
     kyun
    0.82
    as
    0.81
     käyttö
    0.80
    POSITIVE LOGITS
    
    0.76
    Nexus
    0.71
    
    0.71
    iance
    0.70
    '(
    0.69
    了一条
    0.68
    的部分
    0.68
    clature
    0.67
    (.
    0.64
    钟
    0.63
    Activations Density 0.000%

    No Known Activations