© 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. 22-GEMMASCOPE-RES-131K
    7. 72411
    Prev
    Next
    INDEX
    Explanations

    storage space or location

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

    The neuron detects mentions of storage‐related features or ample storage space (e.g. “storage,” “pantry,” “closet,” “cabinet,” “plenty of storage,” 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_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
     dieną
    -1.20
     by
    -1.18
    Some
    -1.16
    what
    -1.12
    ANTAGES
    -0.99
    ếng
    -0.98
    elerik
    -0.96
    ﻴ
    -0.94
     first
    -0.93
     only
    -0.93
    POSITIVE LOGITS
     storage
    1.66
     space
    1.42
     chrétien
    1.26
     storing
    1.19
     bascul
    1.14
     laude
    1.11
    ÜN
    1.08
     pojem
    1.07
    announced
    1.06
     Bakterien
    1.06
    Activations Density 0.007%

    No Known Activations