© 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. 70062
    Prev
    Next
    INDEX
    Explanations

    ground and first floor

    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
    Above
    -0.94
     بالای
    -0.86
    above
    -0.84
    pure
    -0.80
    upstream
    -0.79
     Above
    -0.77
    тала
    -0.76
    rehension
    -0.74
     ABOVE
    -0.74
    上方
    -0.73
    POSITIVE LOGITS
     ground
    3.16
     Ground
    2.34
    Ground
    2.34
    ground
    2.14
     downstairs
    2.06
    GROUND
    1.94
     first
    1.93
     GROUND
    1.80
     First
    1.69
    FIRST
    1.66
    Activations Density 0.023%

    No Known Activations