© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54413
    Prev
    Next
    INDEX
    Explanations

    words starting with atom

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

    The neuron detects occurrences of the root “atom” (e.g. “atom,” “atomic,” “atoms”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     These
    -2.91
    感じで
    -2.45
    which
    -2.45
    形で
    -2.42
     -
    -2.39
    ふう
    -2.34
    就像
    -2.34
    This
    -2.33
    ± 
    -2.31
    のが
    -2.27
    POSITIVE LOGITS
     you
    2.94
     we
    2.69
    为了
    2.58
    釤
    2.42
     facilitate
    2.30
     hermanas
    2.30
    ଝ
    2.30
     verifique
    2.23
     crave
    2.22
     persuade
    2.19
    Activations Density 0.015%

    No Known Activations