© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129536
    Prev
    Next
    INDEX
    Explanations

    related to back

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

    The neuron specializes in spotting the root "back" (and its variants) when it appears in compound words or phrases.

    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
     zuverläs
    -1.28
     require
    -1.27
     their
    -1.27
    お互
    -1.26
     children
    -1.25
    صال
    -1.24
     new
    -1.23
    asantry
    -1.19
     besonderen
    -1.17
    廳
    -1.17
    POSITIVE LOGITS
    back
    1.75
     back
    1.54
    Back
    1.53
     Back
    1.45
    BACK
    1.36
    」
    1.34
     Background
    1.30
    ——”
    1.30
    ”，
    1.30
     atrás
    1.29
    Activations Density 0.081%

    No Known Activations