© 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. 23615
    Prev
    Next
    INDEX
    Explanations

    finding new 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
    brata
    -0.87
    трите
    -0.86
    晃
    -0.75
    ⇝
    -0.75
    ResponseEntity
    -0.75
    동
    -0.73
    scaleX
    -0.73
     axios
    -0.72
     результатов
    -0.71
    ロマ
    -0.70
    POSITIVE LOGITS
     homes
    2.78
     forever
    2.08
     loving
    1.73
    forever
    1.71
    homes
    1.68
     home
    1.64
     permanent
    1.60
     Forever
    1.57
     Homes
    1.54
     adoptive
    1.53
    Activations Density 0.021%

    No Known Activations