© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97739
    Prev
    Next
    INDEX
    Explanations

    photo emission, p orbitals, robust monolithic, blue toe, Q:

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

    The neuron fires on individual tokens naming atomic or molecular orbital/shell labels (e.g. the “S”, “2”, “p”, “F”, “I”, etc. in spectroscopic state notations).

    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
    谷歌
    -0.75
    crisis
    -0.75
    입니다
    -0.71
     n
    -0.71
    伝わ
    -0.69
    violence
    -0.69
    immigration
    -0.69
    ղ
    -0.69
     Krise
    -0.68
    atron
    -0.68
    POSITIVE LOGITS
     hore
    0.87
    helle
    0.84
     tirs
    0.83
     maje
    0.82
    setBlock
    0.82
    RetVal
    0.80
    thmus
    0.80
    levels
    0.79
     totality
    0.78
     parlement
    0.78
    Activations Density 0.020%

    No Known Activations