© 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. 22-GEMMASCOPE-RES-131K
    7. 70613
    Prev
    Next
    INDEX
    Explanations

    assigned physical locations

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

    The neuron responds to mentions of countable “spots” or “units” (e.g. campsites, storage units, seats, stalls, cabins, parking bays, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vertebra
    -0.98
     boules
    -0.91
    G
    -0.90
     heron
    -0.90
     Escrow
    -0.90
    N
    -0.88
     Negotiable
    -0.86
    U
    -0.86
     Inks
    -0.86
     eyel
    -0.85
    POSITIVE LOGITS
     reserved
    1.24
     assigned
    1.19
     holders
    1.16
     expediente
    1.14
    ayout
    1.14
    gunakan
    1.13
     ocupado
    1.13
     allocated
    1.12
     revisa
    1.09
    ії
    1.09
    Activations Density 0.035%

    No Known Activations