© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41376
    Prev
    Next
    INDEX
    Explanations

    giving, transferring, or handing over

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

    This neuron activates on verbs (in English or Russian) that mean “to hand over/transfer” (e.g. hand over, deliver to, переда-, отдать).

    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
    3
    -2.25
    7
    -2.11
    1
    -2.08
    4
    -2.02
    5
    -1.98
    9
    -1.98
    8
    -1.97
    .
    -1.84
    6
    -1.84
    2
    -1.82
    POSITIVE LOGITS
    渲
    1.91
     involucrados
    1.89
    麁
    1.88
     preparados
    1.87
     interesados
    1.85
    賎
    1.84
    esine
    1.84
     secos
    1.77
    崢
    1.77
    烔
    1.74
    Activations Density 0.015%

    No Known Activations