© 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. 7007
    Prev
    Next
    INDEX
    Explanations

    Yubi, Varela, Banni, Washed, Ygg, Chlorella

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

    The neuron responds strongly to short, capitalized letter sequences (especially two- or three-letter prefixes) that mark proper names, scientific terms, or acronyms.

    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
     if
    0.41
     which
    0.36
     jeżeli
    0.36
     /
    0.35
     Sekarang
    0.35
     with
    0.34
    ],
    0.34
     oraz
    0.34
     jeśli
    0.34
    ))
    0.33
    POSITIVE LOGITS
    aming
    0.40
    atiti
    0.38
    aphazard
    0.37
    ipping
    0.36
    aping
    0.36
    ُمْ
    0.35
     পিঁপড়ার
    0.35
    芻
    0.35
     गूगल
    0.35
    configuring
    0.35
    Activations Density 0.326%

    No Known Activations