© 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. 34-GEMMASCOPE-RES-131K
    7. 64115
    Prev
    Next
    INDEX
    Explanations

    locations and destinations

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

    The neuron fires on occurrences of the Japanese particle “に” (and its English counterpart “to”) marking direction, target, or recipient.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    などが
    -1.18
    を
    -1.06
    は
    -1.06
    それに
    -1.05
    体に
    -0.97
    が
    -0.97
     Hers
    -0.88
     blau
    -0.87
    datap
    -0.87
    く
    -0.87
    POSITIVE LOGITS
     llegamos
    1.09
    atleta
    1.05
    で見る
    1.05
    だわ
    0.98
    の基本
    0.96
     échou
    0.96
     accedi
    0.95
    を行いました
    0.93
     Jér
    0.91
     mitään
    0.91
    Activations Density 0.001%

    No Known Activations