© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80824
    Prev
    Next
    INDEX
    Explanations

    RAM and memory specifications

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

    The neuron fires strongly on numeric tokens representing large quantities or specifications (e.g. memory sizes, processor model numbers, review scores).

    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
    őtt
    -0.91
     instancia
    -0.85
    года
    -0.81
    savevideo
    -0.81
     aproxima
    -0.79
     MJ
    -0.77
     dólares
    -0.77
    DialogInterface
    -0.77
     dioses
    -0.77
     设置
    -0.75
    POSITIVE LOGITS
     RAM
    2.31
    RAM
    1.88
     memory
    1.53
     ram
    1.45
     Ram
    1.42
    Ram
    1.38
    ram
    1.20
    内存
    1.20
    メモリ
    1.19
    memory
    1.18
    Activations Density 0.031%

    No Known Activations