© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66973
    Prev
    Next
    INDEX
    Explanations

    container words / containers

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

    The neuron is triggered by words naming container units used for storage or shipping (e.g., boxes, cartons, cases).

    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
    O
    -1.57
    錒
    -1.53
     dacia
    -1.51
     giorgio
    -1.48
     ſte
    -1.48
    жка
    -1.48
    FEATURES
    -1.47
     lorenzo
    -1.45
     inteligen
    -1.43
     chirurgie
    -1.43
    POSITIVE LOGITS
     of
    2.16
     is
    1.53
     otras
    1.44
    </i>
    1.37
     case
    1.33
     from
    1.28
     varias
    1.26
     из
    1.25
     caja
    1.24
     the
    1.23
    Activations Density 0.040%

    No Known Activations