© 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. 93572
    Prev
    Next
    INDEX
    Explanations

    articulation and poseability

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

    The neuron fires on technical specification language for action figures—particularly mentions of articulation points, poseable joints, and similar detailed toy‐feature descriptions.

    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
     lisäksi
    -0.81
    Nederlands
    -0.79
    рое
    -0.77
    venge
    -0.75
    焱
    -0.74
     kurulan
    -0.74
    ıdır
    -0.73
    ifikationer
    -0.73
    maktadır
    -0.73
    Amir
    -0.73
    POSITIVE LOGITS
     peg
    1.03
     articulation
    0.92
     posing
    0.92
     reused
    0.91
     tolerances
    0.91
     geführt
    0.86
     pose
    0.85
     inherited
    0.84
     ports
    0.82
     forearm
    0.82
    Activations Density 0.008%

    No Known Activations