© 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. 92932
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities

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

    The neuron fires on single-word descriptive adjectives (especially positive sensory or qualitative descriptors like “light,” “clean,” “smooth,” “warm,” etc.).

    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
    所以在
    -1.79
    でしょうね
    -1.69
     of
    -1.69
    を
    -1.68
     is
    -1.67
    があります
    -1.64
    が
    -1.59
    という感じ
    -1.55
    や
    -1.54
    <bos>
    -1.53
    POSITIVE LOGITS
     and
    1.83
    来週
    1.78
    づくり
    1.72
    久し
    1.71
    為に
    1.68
    さぁ
    1.67
    ことも
    1.66
    ところに
    1.65
    ＊＊＊＊
    1.63
    を目指す
    1.63
    Activations Density 0.062%

    No Known Activations