© 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. 73845
    Prev
    Next
    INDEX
    Explanations

    types of metals

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

    The neuron activates on occurrences of the word “metal” or “metals,” signaling mentions of metallic elements or compounds.

    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
    ꯸
    -2.38
    y
    -2.11
    
    -2.05
    梘
    -2.02
    u
    -1.97
    "}}>
    -1.91
    儅
    -1.91
    z
    -1.91
    比如说
    -1.91
     hlavně
    -1.91
    POSITIVE LOGITS
     It
    2.73
    However
    2.38
     Both
    2.34
     Therefore
    2.30
     Thus
    2.28
     There
    2.27
     juzgar
    2.20
     Übere
    2.16
     préstamo
    2.16
     Neither
    2.13
    Activations Density 0.021%

    No Known Activations