© 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. 115702
    Prev
    Next
    INDEX
    Explanations

    building floor levels

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of a building’s floor or level (e.g., “ground floor,” “first floor,” “floor,” “apartment” in a floor‐number context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     upstairs
    -1.55
     upper
    -1.41
     верх
    -1.27
     downstairs
    -1.26
     top
    -1.22
     ground
    -1.20
    upper
    -1.19
     uphill
    -1.16
    Upstairs
    -1.16
     bottom
    -1.13
    POSITIVE LOGITS
     level
    1.13
    verdi
    0.93
    hfill
    0.90
    level
    0.86
     where
    0.85
    ➔
    0.82
    bereich
    0.82
     LEVEL
    0.81
     יותר
    0.81
    部分
    0.79
    Activations Density 0.082%

    No Known Activations