© 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. 111401
    Prev
    Next
    INDEX
    Explanations

    manager

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

    The neuron fires on occurrences of “manager” (or its parts) in identifiers or constants.

    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
     dejando
    -1.56
     beendet
    -1.49
     überzeugt
    -1.48
     angezeigt
    -1.48
     assortment
    -1.44
    Ꮙ
    -1.44
    ıyordu
    -1.43
    zeppelin
    -1.42
     quedará
    -1.41
    :),
    -1.41
    POSITIVE LOGITS
     cambiar
    1.36
     carburant
    1.35
    踭
    1.34
     bascul
    1.32
     noté
    1.32
    h
    1.30
    U
    1.28
    Уже
    1.27
     vider
    1.27
     следующий
    1.27
    Activations Density 0.055%

    No Known Activations