© 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. 92979
    Prev
    Next
    INDEX
    Explanations

    particularly or especially descriptive

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

    The neuron fires on strongly evaluative or sentiment-laden words (e.g. positive or notable adjectives and related evaluative terms).

    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
     testé
    -1.39
     parfaite
    -1.36
     arrivée
    -1.34
     flesta
    -1.33
    𓁹
    -1.28
     bolsillos
    -1.27
    无论
    -1.27
     花纹
    -1.27
     帅气
    -1.27
     supplé
    -1.25
    POSITIVE LOGITS
     because
    2.11
     when
    1.94
     particular
    1.67
     for
    1.66
     in
    1.61
     particularly
    1.54
     during
    1.50
     after
    1.49
     now
    1.45
     specifically
    1.44
    Activations Density 0.024%

    No Known Activations