© 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. 22-GEMMASCOPE-RES-131K
    7. 35290
    Prev
    Next
    INDEX
    Explanations

    robots and robotics

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

    The neuron activates strongly on technical terms and jargon related to robotics (e.g., robot, manipulator, tactile sensors, localization, control).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     سے
    -1.29
     Lettres
    -1.26
     diritto
    -1.23
     твое
    -1.22
    燼
    -1.13
     débuts
    -1.09
     внимания
    -1.09
     pensées
    -1.08
    gée
    -1.06
    azos
    -1.05
    POSITIVE LOGITS
    fæ
    1.17
     posY
    1.13
    ";//
    1.10
    Rigidbody
    1.09
     msgs
    1.06
     perform
    1.05
     vision
    1.04
     with
    1.02
     задача
    1.02
    :
    1.01
    Activations Density 0.073%

    No Known Activations