© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95848
    Prev
    Next
    INDEX
    Explanations

    in construction or design

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

    The neuron selectively activates on descriptive adjectives (qualities or properties) in the text.

    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
     which
    -1.67
     from
    -1.43
     Если
    -1.23
     of
    -1.18
     которые
    -1.16
     by
    -1.10
     Pflichten
    -1.06
     during
    -1.05
     for
    -1.01
    も
    -1.01
    POSITIVE LOGITS
     Juegos
    1.29
     =="
    1.22
     alça
    1.20
    éndose
    1.17
     maniere
    1.13
    aş
    1.10
    の作成
    1.09
     agencia
    1.09
    зовые
    1.07
     frança
    1.06
    Activations Density 0.071%

    No Known Activations