© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67172
    Prev
    Next
    INDEX
    Explanations

    physical spaces and areas

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

    This neuron detects mentions of specific “areas” or spaces (e.g. lounge area, seating area, picnic area, living area, rest areas) that describe parts of a venue or property.

    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
     from
    -1.27
     it
    -1.22
     or
    -1.13
     Vereinigte
    -1.07
     not
    -1.05
    curities
    -1.04
     to
    -1.02
    itorious
    -1.01
     may
    -0.97
    )
    -0.96
    POSITIVE LOGITS
     rê
    1.33
    Iam
    1.31
     Públicas
    1.24
     mû
    1.24
     passagers
    1.22
     étudiants
    1.20
     falda
    1.20
    ſe
    1.20
     nú
    1.20
    𞤤
    1.20
    Activations Density 0.011%

    No Known Activations