© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40135
    Prev
    Next
    INDEX
    Explanations

    electric field changes

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

    This neuron detects technical references to electric fields and related modulation concepts (e.g., “electric field,” “electric,” “modulation”).

    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
    </b>
    -1.41
     them
    -1.38
    ógico
    -1.30
     altres
    -1.27
     музея
    -1.20
    ability
    -1.20
    phard
    -1.20
    ánicas
    -1.20
    c
    -1.19
    {$\
    -1.18
    POSITIVE LOGITS
     of
    1.45
     PLAYERS
    1.17
     and
    1.14
    ernacle
    1.13
     merusak
    1.10
     divisions
    1.09
     хотел
    1.09
    prava
    1.08
    ժ
    1.06
    ื้น
    1.05
    Activations Density 0.087%

    No Known Activations