© 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. 75590
    Prev
    Next
    INDEX
    Explanations

    disposable items

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

    The neuron flags words that denote “throw-away” or “disposable” items (and related reuse/disposability terms).

    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
     ResponseEntity
    -0.71
    loy
    -0.69
     Mangel
    -0.69
    जा
    -0.69
     הד
    -0.69
     sought
    -0.69
     haine
    -0.68
     sewing
    -0.68
     зару
    -0.68
    🥅
    -0.67
    POSITIVE LOGITS
     disposable
    3.58
     Disposable
    2.84
    disposable
    2.75
    Disposable
    2.73
     dispos
    2.42
     throw
    2.08
     dispose
    1.96
     desecha
    1.80
     disposal
    1.78
    throwaway
    1.70
    Activations Density 0.028%

    No Known Activations