© 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. 74400
    Prev
    Next
    INDEX
    Explanations

    Romanian names and concepts

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

    The neuron strongly activates on multi-part hyphenated strings (especially hyphen-separated names or web‐style compound terms).

    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
    がっ
    -1.66
    到底是
    -1.65
     diriger
    -1.62
    はどこ
    -1.62
     dépass
    -1.46
     favoriser
    -1.43
    marvel
    -1.40
     この
    -1.39
    以外は
    -1.39
     to
    -1.38
    POSITIVE LOGITS
    adakan
    1.73
     impeccable
    1.62
    会社の
    1.59
    𓆜
    1.53
    \#:
    1.52
    猫咪
    1.51
     processi
    1.51
    zył
    1.48
     soirée
    1.46
    ísticos
    1.46
    Activations Density 0.009%

    No Known Activations