© 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. 68033
    Prev
    Next
    INDEX
    Explanations

    best followed by verb

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

    The neuron detects uses of the superlative “best” and its common follow-on phrases (e.g. “best left to…,” “best described as…,” “best represented on…”)

    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
    やってる
    -1.77
    楽しめる
    -1.59
    ところに
    -1.58
     they
    -1.51
    ceptable
    -1.46
    Ꮏ
    -1.46
    螣
    -1.44
    嘮
    -1.41
    你这个
    -1.41
    をの
    -1.41
    POSITIVE LOGITS
    When
    1.75
     While
    1.63
    1
    1.58
    他
    1.52
     kemarin
    1.48
    形
    1.42
    我
    1.42
    While
    1.41
     described
    1.41
    早
    1.38
    Activations Density 0.017%

    No Known Activations