© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21539
    Prev
    Next
    INDEX
    Explanations

    numbers and methods

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

    This neuron detects section‐heading labels in structured scientific abstracts (e.g. “Objective,” “Methods”).

    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
     คา
    -1.50
     ihrer
    -1.45
    dengan
    -1.41
     odeur
    -1.35
    investors
    -1.34
     ouverture
    -1.27
     terem
    -1.27
     alimento
    -1.26
     éti
    -1.25
     สม
    -1.25
    POSITIVE LOGITS
    帳に追加
    1.79
     this
    1.74
    this
    1.65
     Because
    1.59
    いたします
    1.53
    újo
    1.52
     because
    1.50
     applicazioni
    1.48
    This
    1.48
     Gegenstände
    1.48
    Activations Density 0.026%

    No Known Activations