© 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. 34-GEMMASCOPE-RES-131K
    7. 93089
    Prev
    Next
    INDEX
    Explanations

    words starting with Mem, Memo, Memor

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

    This neuron activates on tokens containing the substring “mem” (e.g. words starting with “mem” such as memristor, memo, memcached, or the abbreviation MEM).

    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
    ゆ
    -0.84
    末
    -0.82
     obiettivi
    -0.82
     right
    -0.82
     kleinen
    -0.80
     rumors
    -0.79
     балан
    -0.77
     stří
    -0.77
    Amendment
    -0.75
     évêque
    -0.75
    POSITIVE LOGITS
     Mem
    1.41
    mem
    1.27
     MEM
    1.18
     mem
    1.12
    Mem
    1.02
     Memory
    1.02
     Memoriam
    0.99
     recollection
    0.91
     Memories
    0.91
     Memo
    0.91
    Activations Density 0.032%

    No Known Activations