© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54065
    Prev
    Next
    INDEX
    Explanations

    guest suites and cottages

    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
     exposé
    -0.81
     franco
    -0.78
     Defaults
    -0.75
     reas
    -0.75
    خره
    -0.75
    Founded
    -0.74
     Collab
    -0.74
     liquidated
    -0.73
     DAMAGES
    -0.73
     志
    -0.73
    POSITIVE LOGITS
     guest
    1.63
     studio
    1.47
     accessory
    1.42
     granny
    1.37
     Guest
    1.37
     separate
    1.35
     apartment
    1.32
     cottage
    1.22
    guest
    1.21
    accessory
    1.20
    Activations Density 0.018%

    No Known Activations