© 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. 10-GEMMASCOPE-RES-131K
    7. 20107
    Prev
    Next
    INDEX
    Explanations

    containers for water or items

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

    The neuron detects mentions of vessels or containers used for holding or scooping liquids.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    in
    -1.21
     kako
    -1.13
    kk
    -1.11
     about
    -1.09
    ks
    -1.06
     hla
    -1.05
    cov
    -1.04
     know
    -1.04
     targeting
    -1.04
    know
    -1.03
    POSITIVE LOGITS
    brania
    1.36
    
    1.25
     with
    1.24
     Чтобы
    1.23
     revêtement
    1.23
    mė
    1.20
     menak
    1.20
     or
    1.19
     menyenangkan
    1.17
     réservoir
    1.16
    Activations Density 0.016%

    No Known Activations