© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63605
    Prev
    Next
    INDEX
    Explanations

    homeless shelter

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     gennem
    -0.75
    хео
    -0.72
    XtraEditors
    -0.72
     Gibraltar
    -0.71
     ISC
    -0.70
    stein
    -0.69
     revis
    -0.69
    ướp
    -0.68
    Weighted
    -0.68
    strijden
    -0.68
    POSITIVE LOGITS
     shelter
    2.42
     shelters
    2.36
     homeless
    2.30
     homelessness
    1.77
     Homeless
    1.70
     Shelter
    1.65
    shelter
    1.52
    Shelter
    1.39
     SHEL
    1.34
     soup
    1.33
    Activations Density 0.031%

    No Known Activations