© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12586
    Prev
    Next
    INDEX
    Explanations

    aims of a study

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

    This neuron specializes in spotting phrases that introduce a paper’s or study’s main aim/objective (e.g. “the principal aim of,” “the primary objective of,” “the main goal of,” 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_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
     who
    -1.68
    ellige
    -1.63
    </th>
    -1.52
    tetur
    -1.52
    ائف
    -1.52
     "','
    -1.52
     поскольку
    -1.47
     how
    -1.45
     still
    -1.43
    कडाउन
    -1.41
    POSITIVE LOGITS
     of
    2.16
     verkau
    1.62
     verlie
    1.52
    𓍊
    1.52
     适合
    1.48
    sssss
    1.45
     kompatibel
    1.45
    🤟
    1.44
    iree
    1.44
     appartement
    1.42
    Activations Density 0.119%

    No Known Activations