© 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. 67176
    Prev
    Next
    INDEX
    Explanations

    adaptation and remakes

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

    The neuron fires on words signaling that a film is an adaptation or remake of another work.

    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
    al
    -1.27
    H
    -1.20
    U
    -1.18
    J
    -1.18
    P
    -1.15
    B
    -1.14
    V
    -1.14
     prazo
    -1.12
    C
    -1.09
    D
    -1.07
    POSITIVE LOGITS
     of
    2.59
    aktifkan
    1.63
    ของ
    1.56
     príncipe
    1.39
     sommeil
    1.39
     favoris
    1.37
    Ça
    1.36
    gün
    1.36
     parfüm
    1.34
     kampus
    1.34
    Activations Density 0.030%

    No Known Activations