© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13466
    Prev
    Next
    INDEX
    Explanations

    disuse and decay

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

    The neuron flags words that evoke neglect, disuse, or decay (e.g. “gathering dust,” “languished,” “rot”).

    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
     about
    -1.82
     pulsante
    -1.57
     reason
    -1.46
     zune
    -1.43
     alamu
    -1.41
     heuti
    -1.36
     Songtext
    -1.34
    LYPH
    -1.33
     
    -1.30
     cincin
    -1.29
    POSITIVE LOGITS
     unsere
    1.58
     for
    1.43
    我们
    1.40
    enada
    1.38
     notre
    1.34
     unserem
    1.34
    durante
    1.34
     nuestro
    1.33
    ОВА
    1.32
     polémica
    1.30
    Activations Density 0.020%

    No Known Activations