© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108259
    Prev
    Next
    INDEX
    Explanations

    homelessness and housing insecurity

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

    The main thing this neuron does is detect mentions of homelessness (and related terms or statistics about the homeless).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rebellious
    -0.80
    THEORY
    -0.80
     refreshment
    -0.75
     сторон
    -0.71
    ACKNOWLEDGMENT
    -0.71
    rebel
    -0.70
     tedious
    -0.70
    нци
    -0.69
     drooping
    -0.69
     enhance
    -0.69
    POSITIVE LOGITS
     homeless
    2.28
     homelessness
    2.23
     Homeless
    1.52
     shelters
    1.09
     youth
    0.98
     shelter
    0.97
     couch
    0.96
     HOM
    0.93
     veterans
    0.92
    ָ
    0.88
    Activations Density 0.018%

    No Known Activations