© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6961
    Prev
    Next
    INDEX
    Explanations

    coding and lineage

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

    The neuron fires strongly on the very first meaningful token at the start of each new text block.

    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
    ceti
    0.77
    utama
    0.76
    ERI
    0.74
    tei
    0.73
    เป
    0.73
    ே
    0.73
    टि
    0.72
     इद
    0.72
    ᅵ
    0.72
    thm
    0.71
    POSITIVE LOGITS
     uses
    0.79
     considérons
    0.77
     relaunch
    0.77
     kickoff
    0.75
     cashback
    0.74
     wskaz
    0.73
     si
    0.72
     scén
    0.71
    徑
    0.71
     тря
    0.71
    Activations Density 0.000%

    No Known Activations