© 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. 45328
    Prev
    Next
    INDEX
    Explanations

    purpose of study

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

    The neuron detects the phrasing of a study’s stated purpose or objective (e.g. “The purpose of this study is to …”).

    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
     üblichen
    -1.68
    urnum
    -1.47
    The
    -1.47
     desbloquear
    -1.45
     derivados
    -1.41
     pervasive
    -1.39
    したもの
    -1.39
    zzá
    -1.39
    It
    -1.38
     prevalent
    -1.38
    POSITIVE LOGITS
     of
    2.66
     Diakses
    1.40
     astu
    1.39
     lakini
    1.38
     herbe
    1.35
    騭
    1.34
     injus
    1.30
     aimé
    1.29
     durer
    1.29
     bedo
    1.26
    Activations Density 0.146%

    No Known Activations