© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8939
    Prev
    Next
    INDEX
    Explanations

    best part of

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

    This neuron detects the phrase “the best part” (i.e. superlative mentions of the best aspect of something).

    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
     in
    -2.27
     a
    -1.95
     berguna
    -1.37
    estyles
    -1.30
    ❮
    -1.27
     jongen
    -1.27
    ’
    -1.26
    𝘪
    -1.23
    </sup>
    -1.23
     füh
    -1.21
    POSITIVE LOGITS
     giebt
    1.54
    >'+
    1.51
    是可以
    1.49
    他的
    1.48
    )
    1.45
    Furthermore
    1.43
    </i>
    1.41
    氲
    1.41
     åren
    1.37
    櫚
    1.36
    Activations Density 0.018%

    No Known Activations