© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1815
    Prev
    Next
    INDEX
    Explanations

    back up

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

    The neuron fires whenever it sees the word “back” (e.g. “back off,” “back up,” “back it up,” 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_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
    .
    -3.20
    “
    -2.33
    (
    -1.95
     Putting
    -1.91
     получил
    -1.84
    🕗
    -1.83
    !"
    -1.82
     Making
    -1.81
     quite
    -1.80
     very
    -1.79
    POSITIVE LOGITS
    ーん
    2.05
    despite
    2.02
     specif
    1.99
    ㉗
    1.99
    ౩
    1.92
     ludicrous
    1.91
     insanely
    1.87
    actéristi
    1.86
    ”;
    1.84
     recomienda
    1.84
    Activations Density 0.005%

    No Known Activations