© 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. 34-GEMMASCOPE-RES-131K
    7. 49535
    Prev
    Next
    INDEX
    Explanations

    stored items or stash

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

    This neuron detects words referring to physical clutter or accumulated household stuff (junk, fabric, bins, stored items, 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_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
    涣
    -0.97
     unterwegs
    -0.89
     Wiktionnaire
    -0.88
    zeppelin
    -0.84
     on
    -0.81
     قائمة
    -0.81
     hela
    -0.80
     leaked
    -0.80
    wifi
    -0.79
     counterfeit
    -0.78
    POSITIVE LOGITS
     stored
    1.40
     storage
    1.23
     attic
    1.17
    場所
    1.08
     forgotten
    1.02
     garage
    1.02
    stored
    1.00
     Stored
    1.00
     basement
    0.99
    ategorised
    0.98
    Activations Density 0.049%

    No Known Activations