© 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. 10-GEMMASCOPE-RES-131K
    7. 99216
    Prev
    Next
    INDEX
    Explanations

    momentum space

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

    The neuron detects mentions of momentum or wave‐vector variables (e.g. k_x, k_y, p, Q) and related “momentum space” 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
    ↵
    -1.64
    but
    -1.59
    ↵↵
    -1.55
    m
    -1.52
    ();
    -1.50
    f
    -1.48
    .”
    -1.48
     durch
    -1.48
    ("
    -1.46
     reasons
    -1.46
    POSITIVE LOGITS
     our
    1.84
    OUTUBE
    1.58
     brevemente
    1.53
    inerario
    1.49
    得罪
    1.49
     Якщо
    1.48
    therford
    1.45
    鹛
    1.43
    Schriften
    1.43
     quedará
    1.41
    Activations Density 0.015%

    No Known Activations