© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7744
    Prev
    Next
    INDEX
    Explanations

    new beginner novice

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

    The neuron is detecting relatively rare, content-heavy words (i.e. low-frequency or “uncommon” tokens).

    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_31_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
     હંમે
    0.57
     कैंसर
    0.51
     লাগিলেন
    0.50
     হইয়াছিলেন
    0.49
    嗪
    0.48
    लेज
    0.47
     सहमति
    0.47
     исче
    0.47
    <0xAE>
    0.47
     ধর্মীয়
    0.47
    POSITIVE LOGITS
     rookie
    2.33
     rookies
    2.31
     newbie
    2.22
     novice
    2.20
     inexperienced
    2.20
     fledgling
    2.20
     nascent
    2.08
     freshly
    2.05
     newbies
    2.05
     novices
    2.02
    Activations Density 0.872%

    No Known Activations