© 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. 40569
    Prev
    Next
    INDEX
    Explanations

    M14, 9th, F-16, 35mm

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

    The neuron activates on numeric model or designation codes (digit sequences and alphanumeric combinations) used in names of weapons, vehicles, and military equipment.

    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
     chociaż
    -1.64
    咂
    -1.63
    再一次
    -1.46
    Neden
    -1.44
     any
    -1.41
    Karakteristik
    -1.41
    Mereka
    -1.41
     orice
    -1.40
    İyi
    -1.38
     gemeenten
    -1.38
    POSITIVE LOGITS
    °,
    1.37
     same
    1.27
    ;++
    1.21
    bfd
    1.19
    ญา
    1.19
     tayo
    1.19
    bably
    1.18
    诽
    1.18
     never
    1.18
     to
    1.17
    Activations Density 0.027%

    No Known Activations