© 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. 10-GEMMASCOPE-RES-131K
    7. 42495
    Prev
    Next
    INDEX
    Explanations

    backup power

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

    The neuron fires on occurrences of the words “back up” (or “backup” in its various spellings).

    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
    .
    -4.03
    '
    -2.50
    1
    -2.50
    翾
    -2.36
    tisgarh
    -2.28
    -2.28
    "
    -2.00
    de
    -1.92
    ча
    -1.88
    )
    -1.84
    POSITIVE LOGITS
    áneamente
    2.11
    ”;
    1.98
    ୌ
    1.96
    荦
    1.92
    xically
    1.91
    before
    1.90
    i
    1.89
     стреми
    1.87
    liciter
    1.87
    GRESS
    1.86
    Activations Density 0.009%
    No Known Activations