© 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. 13395
    Prev
    Next
    INDEX
    Explanations

    aspect ratio or float

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

    The neuron selectively activates on relatively long, multi-syllable content words (i.e. uncommon or morphologically complex terms).

    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
    j
    0.93
    y
    0.86
    m
    0.86
    h
    0.76
    ight
    0.75
    c
    0.74
    ë
    0.72
     Decree
    0.71
    x
    0.71
     åp
    0.70
    POSITIVE LOGITS
    或其他
    1.00
     или
    0.89
    或
    0.89
     లేదా
    0.88
     یا
    0.86
     منسل
    0.86
    หรือ
    0.86
     அல்லது
    0.85
    ോട്ട
    0.84
     ಅಥವಾ
    0.84
    Activations Density 0.000%

    No Known Activations