© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    unpacking data structures

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

    The neuron never fires on any of the sample inputs—it doesn’t detect any 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
     perturbative
    0.82
     reduzir
    0.79
     deterioration
    0.78
     worsens
    0.75
     TRIG
    0.73
     impeach
    0.73
     丨
    0.72
    ppled
    0.72
     diminution
    0.72
     worsening
    0.69
    POSITIVE LOGITS
    و
    0.92
    де
    0.85
     mè
    0.77
    彩
    0.77
    cest
    0.77
    c
    0.73
     паке
    0.71
    cine
    0.70
    packs
    0.70
    תו
    0.69
    Activations Density 0.006%

    No Known Activations