© 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. 93874
    Prev
    Next
    INDEX
    Explanations

    removing items

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

    The neuron fires on words that express the action of taking something away—e.g. “Remove,” “removing,” “removed,” “disconnected,” etc.

    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
     hallways
    -0.89
    endenza
    -0.84
    onchange
    -0.84
     zippers
    -0.83
     underside
    -0.82
     COULD
    -0.79
    ika
    -0.76
    édie
    -0.75
     ditches
    -0.75
    ሓ
    -0.75
    POSITIVE LOGITS
     covers
    1.26
     cover
    1.25
     protective
    0.99
     old
    0.95
     panels
    0.89
     excess
    0.88
     outer
    0.88
     top
    0.88
     covering
    0.84
    Cover
    0.84
    Activations Density 0.040%

    No Known Activations