© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48306
    Prev
    Next
    INDEX
    Explanations

    locations/homes

    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
    mah
    -0.89
    omato
    -0.85
    ah
    -0.85
    noscript
    -0.85
    もある
    -0.82
    ma
    -0.82
    ってた
    -0.81
    嗦
    -0.81
    to
    -0.77
    uldron
    -0.77
    POSITIVE LOGITS
     home
    2.20
     homes
    1.77
    自宅
    1.52
    home
    1.31
     domicilio
    1.23
    homes
    1.13
     otthon
    1.13
    บ้าน
    1.12
     locations
    1.12
     private
    1.12
    Activations Density 0.093%

    No Known Activations