© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1655
    Prev
    Next
    INDEX
    Explanations

    help and resources

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

    This neuron detects mentions of homelessness and related social‐housing or poverty issues.

    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
    proguard
    0.77
    剐
    0.75
    Scientists
    0.70
    🔭
    0.69
     collim
    0.69
    scientist
    0.69
    🎢
    0.67
    ⛷
    0.66
     விஞ்ஞான
    0.66
     маркетин
    0.66
    POSITIVE LOGITS
     homeless
    2.75
     homelessness
    2.61
     Homeless
    2.61
     poverty
    2.19
     Poverty
    2.00
     destitute
    1.87
    overty
    1.75
     गरीबी
    1.74
     pobreza
    1.73
     impoverished
    1.66
    Activations Density 1.361%

    No Known Activations