© 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. 70269
    Prev
    Next
    INDEX
    Explanations

    rent, rental, apartment, property, housing

    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
     applicants
    -0.94
     property
    -0.82
     applicant
    -0.80
    剧照
    -0.78
     descanso
    -0.75
     пят
    -0.75
    ckles
    -0.73
     Config
    -0.73
     வரு
    -0.70
     Asset
    -0.69
    POSITIVE LOGITS
    hten
    0.83
     يش
    0.79
     Roper
    0.78
     despatch
    0.77
     rôles
    0.77
     toronto
    0.76
    fchen
    0.76
    Estr
    0.76
     Estr
    0.75
     إليه
    0.75
    Activations Density 0.007%

    No Known Activations