© 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. 34-GEMMASCOPE-RES-131K
    7. 97939
    Prev
    Next
    INDEX
    Explanations

    forgetting and forgotten

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

    The neuron fires on any form of the root “forget” (e.g. forgotten, unforgettable, forgettables).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     yana
    -0.83
    eba
    -0.83
    BETH
    -0.71
     Accommodations
    -0.71
     می‌شوند
    -0.71
    iration
    -0.70
    Flask
    -0.70
     gps
    -0.70
     Tuy
    -0.69
    uero
    -0.69
    POSITIVE LOGITS
     forget
    2.47
     forgotten
    2.23
     забы
    1.87
     Forget
    1.79
    forget
    1.77
    forgotten
    1.77
    Forget
    1.73
    忘
    1.71
     forgetting
    1.68
     forgot
    1.66
    Activations Density 0.020%

    No Known Activations