© 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. 43489
    Prev
    Next
    INDEX
    Explanations

    list operations: first, tail, shift, take

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

    The neuron strongly activates on tokens for “first‐element” retrieval operations (e.g. first, FirstOrDefault, shift).

    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
     Beispiele
    -1.45
    趿
    -1.38
    把她
    -1.38
     .”
    -1.36
    たまた
    -1.36
     europea
    -1.32
     スケ
    -1.30
    放心
    -1.28
     フレ
    -1.28
     Vereine
    -1.27
    POSITIVE LOGITS
    𖡼
    1.71
    𓋼
    1.66
    AndEndTag
    1.66
    蒹
    1.60
    жите
    1.58
    넋
    1.57
    嫆
    1.56
     vermelhas
    1.51
    when
    1.48
    (ﾟ
    1.47
    Activations Density 0.008%

    No Known Activations