© 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. 102735
    Prev
    Next
    INDEX
    Explanations

    eV or UITableView

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

    Looking at the activations, this neuron strongly activates (with values ranging from ~50 to 348) for the token "eV" and related tokens like "V" in contexts where "eV" (electron volt) appears as a unit of energy measurement in scientific and technical

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    朥
    -2.59
    
    -2.53
     經典
    -2.41
    archiwizowane
    -2.38
     殼
    -2.34
    咘
    -2.34
    ⡸
    -2.33
    Ꮡ
    -2.33
    鄚
    -2.27
     現貨
    -2.23
    POSITIVE LOGITS
     
    2.92
    </strong>
    2.69
    e
    2.52
    ing
    2.41
    心中的
    2.39
    ]
    2.31
    </h1>
    2.31
    ↵↵
    2.30
     '
    2.23
     стал
    2.20
    Activations Density 0.002%

    No Known Activations