© 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. 59647
    Prev
    Next
    INDEX
    Explanations

    nice to see

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

    The neuron detects positive-evaluation phrases built from an adjective like “nice,” “great,” or “refreshing” immediately followed by an infinitive (e.g. “nice to see,” “great to get,” “refreshing to see”).

    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
     you
    -1.84
     or
    -1.50
     möglicherweise
    -1.47
     its
    -1.40
     the
    -1.33
     it
    -1.32
     your
    -1.32
     многих
    -1.32
    给你
    -1.30
    뀔
    -1.26
    POSITIVE LOGITS
    楫
    1.35
     ぽ
    1.32
    zzazione
    1.29
    erschutz
    1.28
    viewDidLoad
    1.23
    chenen
    1.23
     ambao
    1.22
    läufer
    1.22
    zsche
    1.20
     leggermente
    1.20
    Activations Density 0.024%

    No Known Activations