© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    rel + suffix/word part

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

    The neuron fires on occurrences of the “rel-” root in words (e.g. rely, reliability, reluctant, etc.).

    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
     Gond
    0.71
     Canal
    0.63
     गौ
    0.61
    Фу
    0.59
    おお
    0.59
     असुर
    0.59
     Gó
    0.58
    荠
    0.58
     gond
    0.57
     Gerber
    0.57
    POSITIVE LOGITS
     Rel
    1.10
    Rel
    1.05
    REL
    0.98
     rel
    0.98
     Reli
    0.92
     REL
    0.88
    rel
    0.84
    relay
    0.82
     Relief
    0.81
     reliefs
    0.79
    Activations Density 0.166%

    No Known Activations