© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13372
    Prev
    Next
    INDEX
    Explanations

    furniture and storage items

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

    The neuron is looking for numeric measurements or dimension specifications (i.e. numbers and units).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roofing
    0.73
    Roof
    0.72
     Roof
    0.71
     roof
    0.68
     regenv
    0.64
     ड्रोन
    0.64
    ⛺
    0.64
    roof
    0.64
     roofing
    0.63
    🏕
    0.61
    POSITIVE LOGITS
     furniture
    1.57
     Furniture
    1.52
    furniture
    1.46
    Furniture
    1.39
     cabinet
    1.36
     drawer
    1.31
    家具
    1.31
    cabinet
    1.27
     Cabinet
    1.26
     drawers
    1.23
    Activations Density 0.868%

    No Known Activations