© 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. 15236
    Prev
    Next
    INDEX
    Explanations

    continue the story

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

    The neuron is essentially dead—it does not reliably activate for any token and thus does not detect any meaningful pattern.

    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
    積分
    0.84
    हे
    0.83
     remedied
    0.80
    엑
    0.75
    क्ति
    0.74
    न्देल
    0.74
    ্যন্তরীণ
    0.73
    ह
    0.73
    يج
    0.72
    тери
    0.71
    POSITIVE LOGITS
    ﻨ
    0.82
     Wishes
    0.77
     vụ
    0.76
    0.75
    ным
    0.73
    ﺼ
    0.72
     sirve
    0.72
    ﺴ
    0.72
     Notation
    0.71
    EPEND
    0.70
    Activations Density 0.001%

    No Known Activations