© 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. 1180
    Prev
    Next
    INDEX
    Explanations

    permanent address, birds are

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

    This neuron detects mentions of moving or relocating (e.g., moving houses or families from one place to another).

    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
    匁
    0.66
     eseguire
    0.64
    針對
    0.61
    debugger
    0.61
     esegu
    0.59
     contradd
    0.58
     ምልክ
    0.57
     />);
    0.57
    解码
    0.56
    ElementsBy
    0.55
    POSITIVE LOGITS
     relocated
    2.86
     relocation
    2.83
     relocate
    2.80
     relocating
    2.77
     reloc
    2.53
    居住
    2.25
     residence
    2.23
    搬
    2.05
    移
    1.95
     residency
    1.94
    Activations Density 1.521%

    No Known Activations