© 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. 10-GEMMASCOPE-RES-131K
    7. 73362
    Prev
    Next
    INDEX
    Explanations

    Terminator Salvation, Indianapolis

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

    The neuron primarily detects decimal numbers (numeric tokens containing a fractional “.-” component).

    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
     Their
    -1.72
     их
    -1.70
     mereka
    -1.65
    their
    -1.63
     they
    -1.63
    他們的
    -1.61
     themselves
    -1.60
    他们的
    -1.58
    Their
    -1.55
     leurs
    -1.53
    POSITIVE LOGITS
     گیاه
    1.50
    了一声
    1.47
    と言える
    1.41
    unjang
    1.35
    出来て
    1.33
     kanskje
    1.32
     ᾿
    1.30
     nessuna
    1.30
    solicited
    1.30
    ']=='
    1.29
    Activations Density 0.012%

    No Known Activations